| S3Pool | Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding computational savings in subsequent convolutional layers. We view the pooling operation in CNNs as a two-step procedure: first, a pooling window (e.g., $2\times 2$) slides over the feature map with stride one which leaves the spatial resolution intact, and second, downsampling is performed by selecting one pixel from each non-overlapping pooling window in an often uniform and deterministic (e.g., top-left) manner. Our starting point in this work is the observation that this regularly spaced downsampling arising from non-overlapping windows, although intuitive from a signal processing perspective (which has the goal of signal reconstruction), is not necessarily optimal for \emph{learning} (where the goal is to generalize). We study this aspect and propose a novel pooling strategy with stochastic spatial sampling (S3Pool), where the regular downsampling is replaced by a more general stochastic version. We observe that this general stochasticity acts as a strong regularizer, and can also be seen as doing implicit data augmentation by introducing distortions in the feature maps. We further introduce a mechanism to control the amount of distortion to suit different datasets and architectures. To demonstrate the effectiveness of the proposed approach, we perform extensive experiments on several popular image classification benchmarks, observing excellent improvements over baseline models. Experimental code is available at https://…/s3pool. |
| SaberLDA | Latent Dirichlet Allocation (LDA) is a popular tool for analyzing discrete count data such as text and images. Applications require LDA to handle both large datasets and a large number of topics. Though distributed CPU systems have been used, GPU-based systems have emerged as a promising alternative because of the high computational power and memory bandwidth of GPUs. However, existing GPU-based LDA systems cannot support a large number of topics because they use algorithms on dense data structures whose time and space complexity is linear to the number of topics. In this paper, we propose SaberLDA, a GPU-based LDA system that implements a sparsity-aware algorithm to achieve sublinear time complexity and scales well to learn a large number of topics. To address the challenges introduced by sparsity, we propose a novel data layout, a new warp-based sampling kernel, and an efficient sparse count matrix updating algorithm that improves locality, makes efficient utilization of GPU warps, and reduces memory consumption. xperiments show that SaberLDA can learn from billions-token-scale data with up to 10,000 topics, which is almost two orders of magnitude larger than that of the previous GPU-based systems. With a single GPU card, SaberLDA is able to earn 10,000 topics from a dataset of billions of tokens in a few hours, which is only achievable with clusters with tens of machines before. |
| Sac2Vec | Network representation learning (also known as information network embedding) has been the central piece of research in social and information network analytics for the last couple of years. An information network can be viewed as a linked structure of a set of entities. A set of linked web pages and documents, a set of users in a social network are common examples of information network. Typically a node in the information network is formed with a unique id, some content information and the links to its direct neighbors. Information network representation techniques traditionally use only link structure of the network. But the textual or other types of content in each node plays an important role to understand the underlying semantics of the network. In this paper, we propose Sac2Vec, a network representation technique using structure and content. It is a multi-layered graph approach which uses a random walk to generate the node embedding. Our approach is simple and computationally fast, yet able to use the content as a complement to structure and the vice-versa. Experimental evaluations on three real world publicly available datasets show the merit of our approach compared to state-of-the-art algorithms in the domain. |
| SAdam | The Adam algorithm has become extremely popular for large-scale machine learning. Under convexity condition, it has been proved to enjoy a data-dependant $O(\sqrt{T})$ regret bound where $T$ is the time horizon. However, whether strong convexity can be utilized to further improve the performance remains an open problem. In this paper, we give an affirmative answer by developing a variant of Adam (referred to as SAdam) which achieves a data-dependant $O(\log T)$ regret bound for strongly convex functions. The essential idea is to maintain a faster decaying yet under controlled step size for exploiting strong convexity. In addition, under a special configuration of hyperparameters, our SAdam reduces to SC-RMSprop, a recently proposed variant of RMSprop for strongly convex functions, for which we provide the first data-dependent logarithmic regret bound. Empirical results on optimizing strongly convex functions and training deep networks demonstrate the effectiveness of our method. |
| Saec | Production recommendation systems rely on embedding methods to represent various features. An impeding challenge in practice is that the large embedding matrix incurs substantial memory footprint in serving as the number of features grows over time. We propose a similarity-aware embedding matrix compression method called Saec to address this challenge. Saec clusters similar features within a field to reduce the embedding matrix size. Saec also adopts a fast clustering optimization based on feature frequency to drastically improve clustering time. We implement and evaluate Saec on Numerous, the production distributed machine learning system in Tencent, with 10-day worth of feature data from QQ mobile browser. Testbed experiments show that Saec reduces the number of embedding vectors by two orders of magnitude, compresses the embedding size by ~27x, and delivers the same AUC and log loss performance. |
| SAE-NAD | The rapid growth of Location-based Social Networks (LBSNs) provides a great opportunity to satisfy the strong demand for personalized Point-of-Interest (POI) recommendation services. However, with the tremendous increase of users and POIs, POI recommender systems still face several challenging problems: (1) the hardness of modeling non-linear user-POI interactions from implicit feedback; (2) the difficulty of incorporating context information such as POIs’ geographical coordinates. To cope with these challenges, we propose a novel autoencoder-based model to learn the non-linear user-POI relations, namely \textit{SAE-NAD}, which consists of a self-attentive encoder (SAE) and a neighbor-aware decoder (NAD). In particular, unlike previous works equally treat users’ checked-in POIs, our self-attentive encoder adaptively differentiates the user preference degrees in multiple aspects, by adopting a multi-dimensional attention mechanism. To incorporate the geographical context information, we propose a neighbor-aware decoder to make users’ reachability higher on the similar and nearby neighbors of checked-in POIs, which is achieved by the inner product of POI embeddings together with the radial basis function (RBF) kernel. To evaluate the proposed model, we conduct extensive experiments on three real-world datasets with many state-of-the-art baseline methods and evaluation metrics. The experimental results demonstrate the effectiveness of our model. |
| SAFE | Many online platforms have deployed anti-fraud systems to detect and prevent fraudster activities. However, there is usually a gap between the time that a user commits a fraudulent action and the time that the user is suspended by the platform. How to detect fraudsters in time is a challenging problem. Most of the existing approaches adopt classifiers to predict fraudsters given their activity sequences along time. The main drawback of classification models is that the prediction results between consecutive timestamps are often inconsistent. In this paper, we propose a survival analysis based fraud early detection model, SAFE, that maps dynamic user activities to survival probabilities that are guaranteed to be monotonically decreasing along time. SAFE adopts recurrent neural network (RNN) to handle user activity sequences and directly outputs hazard values at each timestamp, and then, survival probability derived from hazard values is deployed to achieve consistent predictions. Because we only observe in the training data the user suspended time instead of the fraudulent activity time, we revise the loss function of the regular survival model to achieve fraud early detection. Experimental results on two real world datasets demonstrate that SAFE outperforms both the survival analysis model and recurrent neural network model alone as well as state-of-the-art fraud early detection approaches. |
| Safe Policy-Model Iteration (SPMI) |
In many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we propose a novel framework, Configurable Markov Decision Processes (Conf-MDPs), to model this new type of interaction with the environment. Furthermore, we provide a new learning algorithm, Safe Policy-Model Iteration (SPMI), to jointly and adaptively optimize the policy and the environment configuration. After having introduced our approach and derived some theoretical results, we present the experimental evaluation in two explicative problems to show the benefits of the environment configurability on the performance of the learned policy. |
| Safe Reinforcement Learning | Safe Reinforcement Learning can be defined as the process of learning policies that maximize the expectation of the return in problems in which it is important to ensure reasonable system performance and/or respect safety constraints during the learning and/or deployment processes. We categorize and analyze two approaches of Safe Reinforcement Learning. The first is based on the modification of the optimality criterion, the classic discounted finite/infinite horizon, with a safety factor. The second is based on the modification of the exploration process through the incorporation of external knowledge or the guidance of a risk metric. We use the proposed classification to survey the existing literature, as well as suggesting future directions for Safe Reinforcement Learning. |
| SafePredict | SafePredict is a novel meta-algorithm that works with any base prediction algorithm for online data to guarantee an arbitrarily chosen correctness rate, $1-\epsilon$, by allowing refusals. Allowing refusals means that the meta-algorithm may refuse to emit a prediction produced by the base algorithm on occasion so that the error rate on non-refused predictions does not exceed $\epsilon$. The SafePredict error bound does not rely on any assumptions on the data distribution or the base predictor. When the base predictor happens not to exceed the target error rate $\epsilon$, SafePredict refuses only a finite number of times. When the error rate of the base predictor changes through time SafePredict makes use of a weight-shifting heuristic that adapts to these changes without knowing when the changes occur yet still maintains the correctness guarantee. Empirical results show that (i) SafePredict compares favorably with state-of-the art confidence based refusal mechanisms which fail to offer robust error guarantees; and (ii) combining SafePredict with such refusal mechanisms can in many cases further reduce the number of refusals. Our software (currently in Python) is included in the supplementary material. |
| SAFFRON | In the online false discovery rate (FDR) problem, one observes a possibly infinite sequence of $p$-values $P_1,P_2,\dots$, each testing a different null hypothesis, and an algorithm must pick a sequence of rejection thresholds $\alpha_1,\alpha_2,\dots$ in an online fashion, effectively rejecting the $k$-th null hypothesis whenever $P_k \leq \alpha_k$. Importantly, $\alpha_k$ must be a function of the past, and cannot depend on $P_k$ or any of the later unseen $p$-values, and must be chosen to guarantee that for any time $t$, the FDR up to time $t$ is less than some pre-determined quantity $\alpha \in (0,1)$. In this work, we present a powerful new framework for online FDR control that we refer to as SAFFRON. Like older alpha-investing (AI) algorithms, SAFFRON starts off with an error budget, called alpha-wealth, that it intelligently allocates to different tests over time, earning back some wealth on making a new discovery. However, unlike older methods, SAFFRON’s threshold sequence is based on a novel estimate of the alpha fraction that it allocates to true null hypotheses. In the offline setting, algorithms that employ an estimate of the proportion of true nulls are called adaptive methods, and SAFFRON can be seen as an online analogue of the famous offline Storey-BH adaptive procedure. Just as Storey-BH is typically more powerful than the Benjamini-Hochberg (BH) procedure under independence, we demonstrate that SAFFRON is also more powerful than its non-adaptive counterparts, such as LORD and other generalized alpha-investing algorithms. Further, a monotone version of the original AI algorithm is recovered as a special case of SAFFRON, that is often more stable and powerful than the original. Lastly, the derivation of SAFFRON provides a novel template for deriving new online FDR rules. |
| SAF-Pooling | Major winning Convolutional Neural Networks (CNNs), such as VGGNet, ResNet, DenseNet, \etc, include tens to hundreds of millions of parameters, which impose considerable computation and memory overheads. This limits their practical usage in training and optimizing for real-world applications. On the contrary, light-weight architectures, such as SqueezeNet, are being proposed to address this issue. However, they mainly suffer from low accuracy, as they have compromised between the processing power and efficiency. These inefficiencies mostly stem from following an ad-hoc designing procedure. In this work, we discuss and propose several crucial design principles for an efficient architecture design and elaborate intuitions concerning different aspects of the design procedure. Furthermore, we introduce a new layer called {\it SAF-pooling} to improve the generalization power of the network while keeping it simple by choosing best features. Based on such principles, we propose a simple architecture called {\it SimpNet}. We empirically show that SimpNet provides a good trade-off between the computation/memory efficiency and the accuracy solely based on these primitive but crucial principles. SimpNet outperforms the deeper and more complex architectures such as VGGNet, ResNet, WideResidualNet \etc, on several well-known benchmarks, while having 2 to 25 times fewer number of parameters and operations. We obtain state-of-the-art results (in terms of a balance between the accuracy and the number of involved parameters) on standard datasets, such as CIFAR10, CIFAR100, MNIST and SVHN. The implementations are available at \href{url}{https://…/SimpNet}. |
| SAGA | In this paper, we propose a unified framework and an algorithm for the problem of group recommendation where a fixed number of items or alternatives can be recommended to a group of users. The problem of group recommendation arises naturally in many real world contexts, and is closely related to the budgeted social choice problem studied in economics. We frame the group recommendation problem as choosing a subgraph with the largest group consensus score in a completely connected graph defined over the item affinity matrix. We propose a fast greedy algorithm with strong theoretical guarantees, and show that the proposed algorithm compares favorably to the state-of-the-art group recommendation algorithms according to commonly used relevance and coverage performance measures on benchmark dataset. |
| Saliency Detection | Within our line of sight there are always things that stand out more than others. If you find yourself gazing over a city from a height for example, you may be drawn to a nearby skyscraper, a flashing light or even a red coat someone is wearing below. Saliency is the aspect of any stimulus that makes it stand out from the crowd. The reason a particular stimulus has such salience may be due to contrast i.e. a white line on a black background or as a result of emotional or cognitive factors. For example, we may hone in on something because we are actively looking for it or because it triggers something in our past or memory. Saliency is most commonly discussed in relation to the visual system but it is employed by every perceptual system such as sound and touch. If we are hungry the smell of a favourite food may be highly salient for example. The mechanisms by which humans grant certain stimuli more attentional focus than others probably holds root in our evolutionary past. Our limited cognitive resources require a way to identify the most relevant stimuli for learning and or survival. The world is full of stimuli everywhere you turn and we cannot attend to all of these at once. How does our visual system know where to focus? |
| Saliency Learning | Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches to provide insights toward the model’s behavior and predictions, which are helpful for determining the reliability of the model’s prediction. However, such methods do not fix and improve the model’s reliability. In this paper, we teach our models to make the right prediction for the right reason by providing explanation training signal and ensuring alignment of the models explanation with the ground truth explanation. Our experimental results on multiple tasks and datasets demonstrate the effectiveness of the proposed method, which produces more reliable predictions while delivering better results compared to traditionally trained models. |
| Saliency Methods | Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. |
| Saliency Prediction | |
| SALSA-TEXT | Inspired by the success of self attention mechanism and Transformer architecture in sequence transduction and image generation applications, we propose novel self attention-based architectures to improve the performance of adversarial latent code- based schemes in text generation. Adversarial latent code-based text generation has recently gained a lot of attention due to their promising results. In this paper, we take a step to fortify the architectures used in these setups, specifically AAE and ARAE. We benchmark two latent code-based methods (AAE and ARAE) designed based on adversarial setups. In our experiments, the Google sentence compression dataset is utilized to compare our method with these methods using various objective and subjective measures. The experiments demonstrate the proposed (self) attention-based models outperform the state-of-the-art in adversarial code-based text generation. |
| Salus | GPU computing is becoming increasingly more popular with the proliferation of deep learning (DL) applications. However, unlike traditional resources such as CPU or the network, modern GPUs do not natively support fine-grained sharing primitives. Consequently, implementing common policies such as time sharing and preemption are expensive. Worse, when a DL application cannot completely use a GPU’s resources, the GPU cannot be efficiently shared between multiple applications, leading to GPU underutilization. We present Salus to enable two GPU sharing primitives: fast job switching and memory sharing, in order to achieve fine-grained GPU sharing among multiple DL applications. Salus implements an efficient, consolidated execution service that exposes the GPU to different DL applications, and enforces fine-grained sharing by performing iteration scheduling and addressing associated memory management issues. We show that these primitives can then be used to implement flexible sharing policies such as fairness, prioritization, and packing for various use cases. Our integration of Salus with TensorFlow and evaluation on popular DL jobs show that Salus can improve the average completion time of DL training jobs by $3.19\times$, GPU utilization for hyper-parameter tuning by $2.38\times$, and GPU utilization of DL inference applications by $42\times$ over not sharing the GPU and $7\times$ over NVIDIA MPS with small overhead. |
| Same Place Different Time (SPDT) |
|
| Sammon Mapping | Sammon mapping or Sammon projection is an algorithm that maps a high-dimensional space to a space of lower dimensionality (➚ “Multidimensional Scaling”) by trying to preserve the structure of inter-point distances in high-dimensional space in the lower-dimension projection. It is particularly suited for use in exploratory data analysis. The method was proposed by John W. Sammon in 1969. It is considered a non-linear approach as the mapping cannot be represented as a linear combination of the original variables as possible in techniques such as principal component analysis, which also makes it more difficult to use for classification applications. |
| Sample Entropy | Sample entropy (SampEn) is a modification of approximate entropy (ApEn), used for assessing the complexity of physiological time-series signals, diagnosing diseased states. SampEn has two advantages over ApEn: data length independence and a relatively trouble-free implementation. Also, there is a small computational difference: In ApEn, the comparison between the template vector (see below) and the rest of the vectors also includes comparison with itself. This guarantees that probabilities {\displaystyle C_{i}’^{m}(r)} C_{{i}}’^{{m}}(r) are never zero. Consequently, it is always possible to take a logarithm of probabilities. Because template comparisons with itself lower ApEn values, the signals are interpreted to be more regular than they actually are. These self-matches are not included in SampEn. There is a multiscale version of SampEn as well, suggested by Costa and others. |
| Sample Size Determination (SSD) |
Sample size determination is the act of choosing the number of observations or replicates to include in a statistical sample. The sample size is an important feature of any empirical study in which the goal is to make inferences about a population from a sample. In practice, the sample size used in a study is determined based on the expense of data collection, and the need to have sufficient statistical power. In complicated studies there may be several different sample sizes involved in the study: for example, in a survey sampling involving stratified sampling there would be different sample sizes for each population. In a census, data are collected on the entire population, hence the sample size is equal to the population size. In experimental design, where a study may be divided into different treatment groups, there may be different sample sizes for each group. ssd |
| Sample Size Optimization (SSO) |
Finding the minimal sample size for a query regarding given error constraints. MISS: Finding Optimal Sample Sizes for Approximate Analytics |
| Sample, Explore, Modify, Model and Assess (SEMMA) |
SEMMA is an acronym that stands for Sample, Explore, Modify, Model and Assess. It is a list of sequential steps developed by SAS Institute Inc., one of the largest producers of statistics and business intelligence software. It guides the implementation of data mining applications. Although SEMMA is often considered to be a general data mining methodology, SAS claims that it is “rather a logical organisation of the functional tool set of” one of their products, SAS Enterprise Miner, “for carrying out the core tasks of data mining”. |
| Sample, Operation, Attribute, and Parameter Dimensions (SOAP) |
The computational requirements for training deep neural networks (DNNs) have grown to the point that it is now standard practice to parallelize training. Existing deep learning systems commonly use data or model parallelism, but unfortunately, these strategies often result in suboptimal parallelization performance. In this paper, we define a more comprehensive search space of parallelization strategies for DNNs called SOAP, which includes strategies to parallelize a DNN in the Sample, Operation, Attribute, and Parameter dimensions. We also propose FlexFlow, a deep learning framework that uses guided randomized search of the SOAP space to find a fast parallelization strategy for a specific parallel machine. To accelerate this search, FlexFlow introduces a novel execution simulator that can accurately predict a parallelization strategy’s performance and is three orders of magnitude faster than prior approaches that have to execute each strategy. We evaluate FlexFlow with six real-world DNN benchmarks on two GPU clusters and show that FlexFlow can increase training throughput by up to 3.8x over state-of-the-art approaches, even when including its search time, and also improves scalability. |
| Sampled Weighted Min-Hashing (SWMH) |
We present Sampled Weighted Min-Hashing (SWMH), a randomized approach to automatically mine topics from large-scale corpora. SWMH generates multiple random partitions of the corpus vocabulary based on term co-occurrence and agglomerates highly overlapping inter-partition cells to produce the mined topics. While other approaches define a topic as a probabilistic distribution over a vocabulary, SWMH topics are ordered subsets of such vocabulary. Interestingly, the topics mined by SWMH underlie themes from the corpus at different levels of granularity. We extensively evaluate the meaningfulness of the mined topics both qualitatively and quantitatively on the NIPS (1.7 K documents), 20 Newsgroups (20 K), Reuters (800 K) and Wikipedia (4 M) corpora. Additionally, we compare the quality of SWMH with Online LDA topics for document representation in classification. |
| Sampling Clustering | We propose an efficient graph-based divisive cluster analysis approach called sampling clustering. It constructs a lite informative dendrogram by recursively dividing a graph into subgraphs. In each recursive call, a graph is sampled first with a set of vertices being removed to disconnect latent clusters, then condensed by adding edges to the remaining vertices to avoid graph fragmentation caused by vertex removals. We also present some sampling and condensing methods and discuss the effectiveness in this paper. Our implementations run in linear time and achieve outstanding performance on various types of datasets. Experimental results show that they outperform state-of-the-art clustering algorithms with significantly less computing resources requirements. |
| Sampling Error | In statistics, sampling error is incurred when the statistical characteristics of a population are estimated from a subset, or sample, of that population. Since the sample does not include all members of the population, statistics on the sample, such as means and quantiles, generally differ from parameters on the entire population. For example, if one measures the height of a thousand individuals from a country of one million, the average height of the thousand is typically not the same as the average height of all one million people in the country. Since sampling is typically done to determine the characteristics of a whole population, the difference between the sample and population values is considered a sampling error. Exact measurement of sampling error is generally not feasible since the true population values are unknown; however, sampling error can often be estimated by probabilistic modeling of the sample. |
| Sampling Importance Resampling (SIR) |
Sampling Importance Resampling allows us to sample from the posterior distribution, p(theta|data) where p(theta|data)?L(theta;data)×p(theta) by resampling from a series of draws from the prior, p(theta). Denote one of those n draws from the prior distribution, p(theta), as thetai. Then draw i from the prior sample is drawn with replacement into the posterior sample with probability qi … |
| SAMSA | Current measures for evaluating text simplification systems focus on evaluating lexical text aspects, neglecting its structural aspects. In this paper we propose the first measure to address structural aspects of text simplification, called SAMSA. It leverages recent advances in semantic parsing to assess simplification quality by decomposing the input based on its semantic structure and comparing it to the output. SAMSA provides a reference-less automatic evaluation procedure, avoiding the problems that reference-based methods face due to the vast space of valid simplifications for a given sentence. Our human evaluation experiments show both SAMSA’s substantial correlation with human judgments, as well as the deficiency of existing reference-based measures in evaluating structural simplification. |
| Samsara | Apache Mahout introduces a new math environment we call Samsara, for its theme of universal renewal. It reflects a fundamental rethinking of how scalable machine learning algorithms are built and customized. Mahout-Samsara is here to help people create their own math while providing some off-the-shelf algorithm implementations. At its core are general linear algebra and statistical operations along with the data structures to support them. You can use is as a library or customize it in Scala with Mahout-specific extensions that look something like R. Mahout-Samsara comes with an interactive shell that runs distributed operations on a Spark cluster. This make prototyping or task submission much easier and allows users to customize algorithms with a whole new degree of freedom. ➚ “Apache Mahout” http://…/apache-mahout-samsara-quick-start.html |
| Sankey Diagram | Sankey diagrams are a specific type of flow diagram, in which the width of the arrows is shown proportionally to the flow quantity. They are typically used to visualize energy or material or cost transfers between processes. |
| SAOKE | In this paper, we consider the problem of open information extraction (OIE) for extracting entity and relation level intermediate structures from sentences in open-domain. We focus on four types of valuable intermediate structures (Relation, Attribute, Description, and Concept), and propose a unified knowledge expression form, SAOKE, to express them. We publicly release a data set which contains more than forty thousand sentences and the corresponding facts in the SAOKE format labeled by crowd-sourcing. To our knowledge, this is the largest publicly available human labeled data set for open information extraction tasks. Using this labeled SAOKE data set, we train an end-to-end neural model using the sequenceto-sequence paradigm, called Logician, to transform sentences into facts. For each sentence, different to existing algorithms which generally focus on extracting each single fact without concerning other possible facts, Logician performs a global optimization over all possible involved facts, in which facts not only compete with each other to attract the attention of words, but also cooperate to share words. An experimental study on various types of open domain relation extraction tasks reveals the consistent superiority of Logician to other states-of-the-art algorithms. The experiments verify the reasonableness of SAOKE format, the valuableness of SAOKE data set, the effectiveness of the proposed Logician model, and the feasibility of the methodology to apply end-to-end learning paradigm on supervised data sets for the challenging tasks of open information extraction. |
| SAP HANA (HANA) |
SAP HANA has completely transformed the database industry by combining database, data processing, and application platform capabilities in a single in-memory platform. The platform also provides libraries for predictive, planning, text processing, spatial, and business analytics – all on the same architecture. This makes it possible for applications and analytics to be rethought without information processing latency, and sense-and-response solutions can work on massive quantities of real-time data for immediate answers without building pre-aggregates. Simply put – this makes SAP HANA the platform for building and deploying next-generation, real-time applications and analytics. |
| SAP River | River is a programming model and a programming language where you define your application (Data Model, Queries & Business Logic) and upon deployment every run-time artifact is deployed onto a DB (such as HANA) and a run-time container (such as XS to run the JavaScript which handles the business logic side). SAP River is an easy way to make SAP HANA Applications. Develop and test an application backend, in a matter of minutes, that runs on SAP HANA – SAP’s in-memory database and application platform. SAP River is a new way of developing native applications on SAP HANA. River consists of a language, a programming model and a set of tools, which allow the developer to focus on the business intent of the application, and largely ignore issues of implementation and optimization. These aspects are taken care of automatically by the language tools, which choose, on compilation, the most appropriate run-time context for each part of the application. River allows a developer to specify the data model, the application business logic as well as access control, all in a single integrated specification. River is compatible with existing SAP HANA objects, like tables, views, stored procedures and XSJS procedures. River code is in fact cross-compiled into these same native runtime objects, which are automatically exposed via an OData API. The result is a simpler development process, increased developer productivity, and application code that is easier to understand and to maintain. |
| Sapphire | RDF data in the linked open data (LOD) cloud is very valuable for many different applications. In order to unlock the full value of this data, users should be able to issue complex queries on the RDF datasets in the LOD cloud. SPARQL can express such complex queries, but constructing SPARQL queries can be a challenge to users since it requires knowing the structure and vocabulary of the datasets being queried. In this paper, we introduce Sapphire, a tool that helps users write syntactically and semantically correct SPARQL queries without prior knowledge of the queried datasets. Sapphire interactively helps the user while typing the query by providing auto-complete suggestions based on the queried data. After a query is issued, Sapphire provides suggestions on ways to change the query to better match the needs of the user. We evaluated Sapphire based on performance experiments and a user study and showed it to be superior to competing approaches. |
| SAPS | Program synthesis from natural language (NL) is practical for humans and, once technically feasible, would significantly facilitate software development and revolutionize end-user programming. We present SAPS, an end-to-end neural network capable of mapping relatively complex, multi-sentence NL specifications to snippets of executable code. The proposed architecture relies exclusively on neural components, and is built upon a tree2tree autoencoder trained on abstract syntax trees, combined with a pretrained word embedding and a bi-directional multi-layer LSTM for NL processing. The decoder features a doubly-recurrent LSTM with a novel signal propagation scheme and soft attention mechanism. When applied to a large dataset of problems proposed in a previous study, SAPS performs on par with or better than the method proposed there, producing correct programs in over 90% of cases. In contrast to other methods, it does not involve any non-neural components to post-process the resulting programs, and uses a fixed-dimensional latent representation as the only link between the NL analyzer and source code generator. |
| SAQL | Recently, advanced cyber attacks, which consist of a sequence of steps that involve many vulnerabilities and hosts, compromise the security of many well-protected businesses. This has led to the solutions that ubiquitously monitor system activities in each host (big data) as a series of events, and search for anomalies (abnormal behaviors) for triaging risky events. Since fighting against these attacks is a time-critical mission to prevent further damage, these solutions face challenges in incorporating expert knowledge to perform timely anomaly detection over the large-scale provenance data. To address these challenges, we propose a novel stream-based query system that takes as input, a real-time event feed aggregated from multiple hosts in an enterprise, and provides an anomaly query engine that queries the event feed to identify abnormal behaviors based on the specified anomalies. To facilitate the task of expressing anomalies based on expert knowledge, our system provides a domain-specific query language, SAQL, which allows analysts to express models for (1) rule-based anomalies, (2) time-series anomalies, (3) invariant-based anomalies, and (4) outlier-based anomalies. We deployed our system in NEC Labs America comprising 150 hosts and evaluated it using 1.1TB of real system monitoring data (containing 3.3 billion events). Our evaluations on a broad set of attack behaviors and micro-benchmarks show that our system has a low detection latency (<2s) and a high system throughput (110,000 events/s; supporting ~4000 hosts), and is more efficient in memory utilization than the existing stream-based complex event processing systems. |
| SA-Siam | Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance branch. Each branch is a similarity-learning Siamese network. An important design choice in SA-Siam is to separately train the two branches to keep the heterogeneity of the two types of features. In addition, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are computed according to the channel activations around the target position. While the inherited architecture from SiamFC \cite{SiamFC} allows our tracker to operate beyond real-time, the twofold design and the attention mechanism significantly improve the tracking performance. The proposed SA-Siam outperforms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks. |
| Saturating Adaptive Field Estimator (SAFE) |
We study resilient distributed field estimation under measurement attacks. A network of agents or devices measures a large, spatially distributed physical field parameter. An adversary arbitrarily manipulates the measurements of some of the agents. Each agent’s goal is to process its measurements and information received from its neighbors to estimate only a few specific components of the field. We present $\mathbf{SAFE}$, the Saturating Adaptive Field Estimator, a consensus+innovations distributed field estimator that is resilient to measurement attacks. Under sufficient conditions on the compromised measurement streams, the physical coupling between the field and the agents’ measurements, and the connectivity of the cyber communication network, $\mathbf{SAFE}$ guarantees that each agent’s estimate converges almost surely to the true value of the components of the parameter in which the agent is interested. Finally, we illustrate the performance of $\mathbf{SAFE}$ through numerical examples. |
| Satyam | The democratization of machine learning (ML) has led to ML-based machine vision systems for autonomous driving, traffic monitoring, and video surveillance. However, true democratization cannot be achieved without greatly simplifying the process of collecting groundtruth for training and testing these systems. This groundtruth collection is necessary to ensure good performance under varying conditions. In this paper, we present the design and evaluation of Satyam, a first-of-its-kind system that enables a layperson to launch groundtruth collection tasks for machine vision with minimal effort. Satyam leverages a crowdtasking platform, Amazon Mechanical Turk, and automates several challenging aspects of groundtruth collection: creating and launching of custom web-UI tasks for obtaining the desired groundtruth, controlling result quality in the face of spammers and untrained workers, adapting prices to match task complexity, filtering spammers and workers with poor performance, and processing worker payments. We validate Satyam using several popular benchmark vision datasets, and demonstrate that groundtruth obtained by Satyam is comparable to that obtained from trained experts and provides matching ML performance when used for training. |
| SAVOIAS | Visual complexity identifies the level of intricacy and details in an image or the level of difficulty to describe the image. It is an important concept in a variety of areas such as cognitive psychology, computer vision and visualization, and advertisement. Yet, efforts to create large, downloadable image datasets with diverse content and unbiased groundtruthing are lacking. In this work, we introduce Savoias, a visual complexity dataset that compromises of more than 1,400 images from seven image categories relevant to the above research areas, namely Scenes, Advertisements, Visualization and infographics, Objects, Interior design, Art, and Suprematism. The images in each category portray diverse characteristics including various low-level and high-level features, objects, backgrounds, textures and patterns, text, and graphics. The ground truth for Savoias is obtained by crowdsourcing more than 37,000 pairwise comparisons of images using the forced-choice methodology and with more than 1,600 contributors. The resulting relative scores are then converted to absolute visual complexity scores using the Bradley-Terry method and matrix completion. When applying five state-of-the-art algorithms to analyze the visual complexity of the images in the Savoias dataset, we found that the scores obtained from these baseline tools only correlate well with crowdsourced labels for abstract patterns in the Suprematism category (Pearson correlation r=0.84). For the other categories, in particular, the objects and advertisement categories, low correlation coefficients were revealed (r=0.3 and 0.56, respectively). These findings suggest that (1) state-of-the-art approaches are mostly insufficient and (2) Savoias enables category-specific method development, which is likely to improve the impact of visual complexity analysis on specific application areas, including computer vision. |
| SAX Transformation | ➘ “Symbolic Aggregate Approximation” TSMining |
| s-bAbI | In this study, we investigate the limits of the current state of the art AI system for detecting buffer overflows and compare it with current static analysis tools. To do so, we developed a code generator, s-bAbI, capable of producing an arbitrarily large number of code samples of controlled complexity. We found that the static analysis engines we examined have good precision, but poor recall on this dataset, except for a sound static analyzer that has good precision and recall. We found that the state of the art AI system, a memory network modeled after Choi et al. [1], can achieve similar performance to the static analysis engines, but requires an exhaustive amount of training data in order to do so. Our work points towards future approaches that may solve these problems; namely, using representations of code that can capture appropriate scope information and using deep learning methods that are able to perform arithmetic operations. |
| SBG-Sketch | Applications in various domains rely on processing graph streams, e.g., communication logs of a cloud-troubleshooting system, road-network traffic updates, and interactions on a social network. A labeled-graph stream refers to a sequence of streamed edges that form a labeled graph. Label-aware applications need to filter the graph stream before performing a graph operation. Due to the large volume and high velocity of these streams, it is often more practical to incrementally build a lossy-compressed version of the graph, and use this lossy version to approximately evaluate graph queries. Challenges arise when the queries are unknown in advance but are associated with filtering predicates based on edge labels. Surprisingly common, and especially challenging, are labeled-graph streams that have highly skewed label distributions that might also vary over time. This paper introduces Self-Balanced Graph Sketch (SBG-Sketch, for short), a graphical sketch for summarizing and querying labeled-graph streams that can cope with all these challenges. SBG-Sketch maintains synopsis for both the edge attributes (e.g., edge weight) as well as the topology of the streamed graph. SBG-Sketch allows efficient processing of graph-traversal queries, e.g., reachability queries. Experimental results over a variety of real graph streams show SBG-Sketch to reduce the estimation errors of state-of-the-art methods by up to 99%. |
| sCAKE | Keyword Extraction is an important task in several text analysis endeavors. In this paper, we present a critical discussion of the issues and challenges ingraph-based keyword extraction methods, along with comprehensive empirical analysis. We propose a parameterless method for constructing graph of text that captures the contextual relation between words. A novel word scoring method is also proposed based on the connection between concepts. We demonstrate that both proposals are individually superior to those followed by the state-of-the-art graph-based keyword extraction algorithms. Combination of the proposed graph construction and scoring methods leads to a novel, parameterless keyword extraction method (sCAKE) based on semantic connectivity of words in the document. Motivated by limited availability of NLP tools for several languages, we also design and present a language-agnostic keyword extraction (LAKE) method. We eliminate the need of NLP tools by using a statistical filter to identify candidate keywords before constructing the graph. We show that the resulting method is a competent solution for extracting keywords from documents oflanguages lacking sophisticated NLP support. |
| Scala | Scala is an object-functional programming language for general software applications. Scala has full support for functional programming and a very strong static type system. This allows programs written in Scala to be very concise and thus smaller in size than other general-purpose programming languages. Many of Scala’s design decisions were inspired by criticism of the shortcomings of Java. Scala source code is intended to be compiled to Java bytecode, so that the resulting executable code runs on a Java virtual machine. Java libraries may be used directly in Scala code and vice versa (language interoperability). Like Java, Scala is object-oriented, and uses a curly-brace syntax reminiscent of the C programming language. Unlike Java, Scala has many features of functional programming languages like Scheme, Standard ML and Haskell, including currying, type inference, immutability, lazy evaluation, and pattern matching. It also has an advanced type system supporting algebraic data types, covariance and contravariance, higher-order types, and anonymous types. Other features of Scala not present in Java include operator overloading, optional parameters, named parameters, raw strings, and no checked exceptions. The name Scala is a portmanteau of ‘scalable’ and ‘language’, signifying that it is designed to grow with the demands of its users. |
| Scalable Advanced Massive Online Analysis (SAMOA) |
SAMOA (Scalable Advanced Massive Online Analysis) is a platform for mining big data streams. It provides a collection of distributed streaming algorithms for the most common data mining and machine learning tasks such as classification, clustering, and regression, as well as programming abstractions to develop new algorithms. It features a pluggable architecture that allows it to run on several distributed stream processing engines such as Storm, S4, and Samza. samoa is written in Java, is open source, and is available at http://samoa-project.net under the Apache Software License version 2.0. http://samoa.incubator.apache.org http://samoa-project.net https://…able-advanced-massive-online-analysis.pdf |
| Scalable Bayesian Multi-relational Factorization with Side Information using MCMC (Macau) |
We propose Macau, a powerful and flexible Bayesian factorization method for heterogeneous data. Our model can factorize any set of entities and relations that can be represented by a relational model, including tensors and also multiple relations for each entity. Macau can also incorporate side information, specifically entity and relation features, which are crucial for predicting sparsely observed relations. Macau scales to millions of entity instances, hundred millions of observations, and sparse entity features with millions of dimensions. To achieve the scale up, we specially designed sampling procedure for entity and relation features that relies primarily on noise injection in linear regressions. We show performance and advanced features of Macau in a set of experiments, including challenging drug-protein activity prediction task. |
| Scalable Fair Clustering | We study the fair variant of the classic $k$-median problem introduced by Chierichetti et al. [2017]. In the standard $k$-median problem, given an input pointset $P$, the goal is to find $k$ centers $C$ and assign each input point to one of the centers in $C$ such that the average distance of points to their cluster center is minimized. In the fair variant of $k$-median, the points are colored, and the goal is to minimize the same average distance objective while ensuring that all clusters have an ‘approximately equal’ number of points of each color. Chierichetti et al. proposed a two-phase algorithm for fair $k$-clustering. In the first step, the pointset is partitioned into subsets called fairlets that satisfy the fairness requirement and approximately preserve the $k$-median objective. In the second step, fairlets are merged into $k$ clusters by one of the existing $k$-median algorithms. The running time of this algorithm is dominated by the first step, which takes super-quadratic time. In this paper, we present a practical approximate fairlet decomposition algorithm that runs in nearly linear time. Our algorithm additionally allows for finer control over the balance of resulting clusters than the original work. We complement our theoretical bounds with empirical evaluation. |
| Scalable Generalized Dynamic Topic Model | Dynamic topic models (DTMs) model the evolution of prevalent themes in literature, online media, and other forms of text over time. DTMs assume that word co-occurrence statistics change continuously and therefore impose continuous stochastic process priors on their model parameters. These dynamical priors make inference much harder than in regular topic models, and also limit scalability. In this paper, we present several new results around DTMs. First, we extend the class of tractable priors from Wiener processes to the generic class of Gaussian processes (GPs). This allows us to explore topics that develop smoothly over time, that have a long-term memory or are temporally concentrated (for event detection). Second, we show how to perform scalable approximate inference in these models based on ideas around stochastic variational inference and sparse Gaussian processes. This way we can train a rich family of DTMs to massive data. Our experiments on several large-scale datasets show that our generalized model allows us to find interesting patterns that were not accessible by previous approaches. |
| Scalable Geographically Weighted Regression (ScaGWR) |
While a number of studies have developed fast geographically weighted regression (GWR) algorithms for large samples, none of them achieves the linear-time estimation that is considered requisite for big data analysis in machine learning, geostatistics, and related domains. Against this backdrop, this study proposes a scalable geographically weighted regression (ScaGWR) for large datasets. The key development is the calibration of the model through a pre-compression of the matrices and vectors whose size depends on the sample size, prior to the execution of leave-one-out cross-validation (LOOCV) that is the heaviest computational step in conventional GWR. This pre-compression allows us to run the proposed GWR extension such that its computation time increases linearly with sample size, whereas conventional GWR algorithms take at most quad-quadratic-order time. With this development, the ScaGWR can be calibrated with more than one million samples without parallelization. Moreover, the ScaGWR estimator can be regarded as an empirical Bayesian estimator that is more stable than the conventional GWR estimator. This study compared the ScaGWR with the conventional GWR in terms of estimation accuracy, predictive accuracy, and computational efficiency using a Monte Carlo simulation. Then, we apply these methods to a residential land analysis in the Tokyo Metropolitan Area. The code for ScaGWR is available in the R package scgwr, and is going to be incorporated into another R package, GWmodel. |
| Scalable Gromov-Wasserstein Learning (S-GWL) |
We propose a scalable Gromov-Wasserstein learning (S-GWL) method and establish a novel and theoretically-supported paradigm for large-scale graph analysis. The proposed method is based on the fact that Gromov-Wasserstein discrepancy is a pseudometric on graphs. Given two graphs, the optimal transport associated with their Gromov-Wasserstein discrepancy provides the correspondence between their nodes and achieves graph matching. When one of the graphs has isolated but self-connected nodes ($i.e.$, a disconnected graph), the optimal transport indicates the clustering structure of the other graph and achieves graph partitioning. Using this concept, we extend our method to multi-graph partitioning and matching by learning a Gromov-Wasserstein barycenter graph for multiple observed graphs; the barycenter graph plays the role of the disconnected graph, and since it is learned, so is the clustering. Our method combines a recursive $K$-partition mechanism with a regularized proximal gradient algorithm, whose time complexity is $\mathcal{O}(K(E+V)\log_K V)$ for graphs with $V$ nodes and $E$ edges. To our knowledge, our method is the first attempt to make Gromov-Wasserstein discrepancy applicable to large-scale graph analysis and unify graph partitioning and matching into the same framework. It outperforms state-of-the-art graph partitioning and matching methods, achieving a trade-off between accuracy and efficiency. |
| Scalable Incomplete Network Embedding (SINE) |
Attributed network embedding aims to learn low-dimensional vector representations for nodes in a network, where each node contains rich attributes/features describing node content. Because network topology structure and node attributes often exhibit high correlation, incorporating node attribute proximity into network embedding is beneficial for learning good vector representations. In reality, large-scale networks often have incomplete/missing node content or linkages, yet existing attributed network embedding algorithms all operate under the assumption that networks are complete. Thus, their performance is vulnerable to missing data and suffers from poor scalability. In this paper, we propose a Scalable Incomplete Network Embedding (SINE) algorithm for learning node representations from incomplete graphs. SINE formulates a probabilistic learning framework that separately models pairs of node-context and node-attribute relationships. Different from existing attributed network embedding algorithms, SINE provides greater flexibility to make the best of useful information and mitigate negative effects of missing information on representation learning. A stochastic gradient descent based online algorithm is derived to learn node representations, allowing SINE to scale up to large-scale networks with high learning efficiency. We evaluate the effectiveness and efficiency of SINE through extensive experiments on real-world networks. Experimental results confirm that SINE outperforms state-of-the-art baselines in various tasks, including node classification, node clustering, and link prediction, under settings with missing links and node attributes. SINE is also shown to be scalable and efficient on large-scale networks with millions of nodes/edges and high-dimensional node features. The source code of this paper is available at https://…/SINE. |
| Scalable Logo Self-co-Learning (SL^2) |
Existing logo detection methods usually consider a small number of logo classes and limited images per class with a strong assumption of requiring tedious object bounding box annotations, therefore not scalable to real-world dynamic applications. In this work, we tackle these challenges by exploring the webly data learning principle without the need for exhaustive manual labelling. Specifically, we propose a novel incremental learning approach, called Scalable Logo Self-co-Learning (SL^2), capable of automatically self-discovering informative training images from noisy web data for progressively improving model capability in a cross-model co-learning manner. Moreover, we introduce a very large (2,190,757 images of 194 logo classes) logo dataset ‘WebLogo-2M’ by an automatic web data collection and processing method. Extensive comparative evaluations demonstrate the superiority of the proposed SL^2 method over the state-of-the-art strongly and weakly supervised detection models and contemporary webly data learning approaches. |
| Scalable Machine Learning | Scalability has become one of those core concept slash buzzwords of Big Data. It’s all about scaling out, web scale, and so on. In principle, the idea is to be able to take one piece of code and then throw any number of computers at it to make it fast. The terms “scalable” and “large scale” have been used in machine learning circles long before there was Big Data. There had always been certain problems which lead to a large amount of data, for example in bioinformatics, or when dealing with large number of text documents. So finding learning algorithms, or more generally data analysis algorithms which can deal with a very large set of data was always a relevant question. |
| Scalable Online Learning (SOL) |
SOL is an open-source library for scalable online learning algorithms, and is particularly suitable for learning with high-dimensional data. The library provides a family of regular and sparse online learning algorithms for large-scale binary and multi-class classification tasks with high efficiency, scalability, portability, and extensibility. SOL was implemented in C++, and provided with a collection of easy-to-use command-line tools, python wrappers and library calls for users and developers, as well as comprehensive documents for both beginners and advanced users. SOL is not only a practical machine learning toolbox, but also a comprehensive experimental platform for online learning research. Experiments demonstrate that SOL is highly efficient and scalable for large-scale machine learning with high-dimensional data. |
| Scalding | Scalding is a Scala library that makes it easy to specify Hadoop MapReduce jobs. Scalding is built on top of Cascading, a Java library that abstracts away low-level Hadoop details. Scalding is comparable to Pig, but offers tight integration with Scala, bringing advantages of Scala to your MapReduce jobs. |
| Scale Adaptive Dictionary Learning (SADL) |
Dictionary learning has been widely used in many image processing tasks. In most of these methods, the number of basis vectors is either set by experience or coarsely evaluated empirically. In this paper we propose a new Scale Adaptive Dictionary Learning (SADL) framework, which jointly estimates suitable scales and corresponding atoms in an adaptive fashion according to the training data, without the need of prior information. We design an atom counting function and develop a reliable numerical scheme to solve the challenging optimization problem. Extensive experiments on texture and video datasets demonstrate quantitatively and visually that our method can estimate the scale, without damaging the sparse reconstruction ability. |
| Scale Aware Feature Encoder (SAFE) |
In this paper, we address the problem of having characters with different scales in scene text recognition. We propose a novel scale aware feature encoder (SAFE) that is designed specifically for encoding characters with different scales. SAFE is composed of a multi-scale convolutional encoder and a scale attention network. The multi-scale convolutional encoder targets at extracting character features under multiple scales, and the scale attention network is responsible for selecting features from the most relevant scale(s). SAFE has two main advantages over the traditional single-CNN encoder used in current state-of-the-art text recognizers. First, it explicitly tackles the scale problem by extracting scale-invariant features from the characters. This allows the recognizer to put more effort in handling other challenges in scene text recognition, like those caused by view distortion and poor image quality. Second, it can transfer the learning of feature encoding across different character scales. This is particularly important when the training set has a very unbalanced distribution of character scales, as training with such a dataset will make the encoder biased towards extracting features from the predominant scale. To evaluate the effectiveness of SAFE, we design a simple text recognizer named scale-spatial attention network (S-SAN) that employs SAFE as its feature encoder, and carry out experiments on six public benchmarks. Experimental results demonstrate that S-SAN can achieve state-of-the-art (or, in some cases, extremely competitive) performance without any post-processing. |
| Scale Invariant Probabilistic Neural Network (SPNN) |
Proposed by Specht (1990) <doi:10.1016/0893-6080(90)90049-q>. spnn |
| Scale-Adaptive Neural Dense Features (SAND Features) |
How do computers and intelligent agents view the world around them? Feature extraction and representation constitutes one the basic building blocks towards answering this question. Traditionally, this has been done with carefully engineered hand-crafted techniques such as HOG, SIFT or ORB. However, there is no “one size fits all” approach that satisfies all requirements. In recent years, the rising popularity of deep learning has resulted in a myriad of end-to-end solutions to many computer vision problems. These approaches, while successful, tend to lack scalability and can’t easily exploit information learned by other systems. Instead, we propose SAND features, a dedicated deep learning solution to feature extraction capable of providing hierarchical context information. This is achieved by employing sparse relative labels indicating relationships of similarity/dissimilarity between image locations. The nature of these labels results in an almost infinite set of dissimilar examples to choose from. We demonstrate how the selection of negative examples during training can be used to modify the feature space and vary it’s properties. To demonstrate the generality of this approach, we apply the proposed features to a multitude of tasks, each requiring different properties. This includes disparity estimation, semantic segmentation, self-localisation and SLAM. In all cases, we show how incorporating SAND features results in better or comparable results to the baseline, whilst requiring little to no additional training. Code can be found at: https://…/SAND_features |
| Scaled Cayley Orthogonal Recurrent Neural Network (scoRNN) |
Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or exploding gradients. Recent work on Unitary Recurrent Neural Networks (uRNNs) have been used to address this issue and in some cases, exceed the capabilities of Long Short-Term Memory networks (LSTMs). We propose a simpler and novel update scheme to maintain orthogonal recurrent weight matrices without using complex valued matrices. This is done by parametrizing with a skew-symmetric matrix using the Cayley transform. Such a parametrization is unable to represent matrices with negative one eigenvalues, but this limitation is overcome by scaling the recurrent weight matrix by a diagonal matrix consisting of ones and negative ones. The proposed training scheme involves a straightforward gradient calculation and update step. In several experiments, the proposed scaled Cayley orthogonal recurrent neural network (scoRNN) achieves superior results with fewer trainable parameters than other unitary RNNs. |
| Scaled Exponentially-Regularized Linear Unit (SERLU) |
Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently incorporate normalization based on central limit theory. SELU is a monotonically increasing function, where it has an approximately constant negative output for large negative input. In this work, we propose a new activation function to break the monotonicity property of SELU while still preserving the self-normalizing property. Differently from SELU, the new function introduces a bump-shaped function in the region of negative input by regularizing a linear function with a scaled exponential function, which is referred to as a scaled exponentially-regularized linear unit (SERLU). The bump-shaped function has approximately zero response to large negative input while being able to push the output of SERLU towards zero mean statistically. To effectively combat over-fitting, we develop a so-called shift-dropout for SERLU, which includes standard dropout as a special case. Experimental results on MNIST, CIFAR10 and CIFAR100 show that SERLU-based neural networks provide consistently promising results in comparison to other 5 activation functions including ELU, SELU, Swish, Leakly ReLU and ReLU. |
| Scaled Sparse Linear Regression | Scaled sparse linear regression jointly estimates the regression coefficients and noise level in a linear model. It chooses an equilibrium with a sparse regression method by iteratively estimating the noise level via the mean residual square and scaling the penalty in proportion to the estimated noise level. The iterative algorithm costs little beyond the computation of a path or grid of the sparse regression estimator for penalty levels above a proper threshold. For the scaled lasso, the algorithm is a gradient descent in a convex minimization of a penalized joint loss function for the regression coefficients and noise level. Under mild regularity conditions, we prove that the scaled lasso simultaneously yields an estimator for the noise level and an estimated coefficient vector satisfying certain oracle inequalities for prediction, the estimation of the noise level and the regression coefficients. These inequalities provide sufficient conditions for the consistency and asymptotic normality of the noise level estimator, including certain cases where the number of variables is of greater order than the sample size. Parallel results are provided for the least squares estimation after model selection by the scaled lasso. Numerical results demonstrate the superior performance of the proposed methods over an earlier proposal of joint convex minimization. |
| Scale-Free Identifier Network (sfIN) |
We propose scale-free Identifier Network(sfIN), a novel model for event identification in documents. In general, sfIN first encodes a document into multi-scale memory stacks, then extracts special events via conducting multi-scale actions, which can be considered as a special type of sequence labelling. The design of large scale actions makes it more efficient processing a long document. The whole model is trained with both supervised learning and reinforcement learning. |
| ScaleNet | Successful visual recognition networks benefit from aggregating information spanning from a wide range of scales. Previous research has investigated information fusion of connected layers or multiple branches in a block, seeking to strengthen the power of multi-scale representations. Despite their great successes, existing practices often allocate the neurons for each scale manually, and keep the same ratio in all aggregation blocks of an entire network, rendering suboptimal performance. In this paper, we propose to learn the neuron allocation for aggregating multi-scale information in different building blocks of a deep network. The most informative output neurons in each block are preserved while others are discarded, and thus neurons for multiple scales are competitively and adaptively allocated. Our scale aggregation network (ScaleNet) is constructed by repeating a scale aggregation (SA) block that concatenates feature maps at a wide range of scales. Feature maps for each scale are generated by a stack of downsampling, convolution and upsampling operations. The data-driven neuron allocation and SA block achieve strong representational power at the cost of considerably low computational complexity. The proposed ScaleNet, by replacing all 3×3 convolutions in ResNet with our SA blocks, achieves better performance than ResNet and its outstanding variants like ResNeXt and SE-ResNet, in the same computational complexity. On ImageNet classification, ScaleNets absolutely reduce the top-1 error rate of ResNets by 1.12 (101 layers) and 1.82 (50 layers). On COCO object detection, ScaleNets absolutely improve the mmAP with backbone of ResNets by 3.6 (101 layers) and 4.6 (50 layers) on Faster RCNN, respectively. Code and models are released at https://…/ScaleNet. |
| Scaling Invariable Benford Distance | For the first time, we introduce ‘Scaling invariable Benford distance’ and ‘Benford cyclic graph’, which can be used to analyze any data set. Using the quantity and the graph, we analyze some date sets with common distributions, such as normal, exponent, etc., find that different data set has a much different value of ‘Scaling invariable Benford distance’ and different figure feature of ‘Benford cyclic graph’. We also explore the influence of data size on ‘Scaling invariable Benford distance’, and find that it firstly reduces with data size increasing, then approximate to a fixed value when the size is large enough. |
| Scaling Up Secure Approximate k-Nearest Neighbors Search (SANNS) |
We present new secure protocols for approximate $k$-nearest neighbor search ($k$-NNS) over the Euclidean distance in the semi-honest model. Our implementation is able to handle massive datasets efficiently. On the algorithmic front, we show a new circuit for the approximate top-$k$ selection from $n$ numbers that is built from merely $O(n + \mathrm{poly}(k))$ comparators. Using this circuit as a subroutine, we design new approximate $k$-NNS algorithms and two corresponding secure protocols: 1) optimized linear scan; 2) clustering-based sublinear time algorithm. Our secure protocols utilize a combination of additively-homomorphic encryption, garbled circuit and Oblivious RAM. Along the way, we introduce various optimizations to these primitives, which drastically improve concrete efficiency. We evaluate the new protocols empirically and show that they are able to handle datasets that are significantly larger than in the prior work. For instance, running on two standard Azure instances within the same availability zone, for a dataset of $96$-dimensional descriptors of $10\,000\,000$ images, we can find $10$ nearest neighbors with average accuracy $0.9$ in under $10$ seconds improving upon prior work by at least two orders of magnitude. |
| SCAR | Machine learning (ML) training algorithms often possess an inherent self-correcting behavior due to their iterative-convergent nature. Recent systems exploit this property to achieve adaptability and efficiency in unreliable computing environments by relaxing the consistency of execution and allowing calculation errors to be self-corrected during training. However, the behavior of such systems are only well understood for specific types of calculation errors, such as those caused by staleness, reduced precision, or asynchronicity, and for specific types of training algorithms, such as stochastic gradient descent. In this paper, we develop a general framework to quantify the effects of calculation errors on iterative-convergent algorithms and use this framework to design new strategies for checkpoint-based fault tolerance. Our framework yields a worst-case upper bound on the iteration cost of arbitrary perturbations to model parameters during training. Our system, SCAR, employs strategies which reduce the iteration cost upper bound due to perturbations incurred when recovering from checkpoints. We show that SCAR can reduce the iteration cost of partial failures by 78% – 95% when compared with traditional checkpoint-based fault tolerance across a variety of ML models and training algorithms. |
| Scattering Network | Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. Scattering Networks for Hybrid Representation Learning |
| Scattering Transforms (ScatterNets) |
Scattering Transforms (or ScatterNets) introduced by Mallat are a promising start into creating a well-defined feature extractor to use for pattern recognition and image classification tasks. They are of particular interest due to their architectural similarity to Convolutional Neural Networks (CNNs), while requiring no parameter learning and still performing very well (particularly in constrained classification tasks). In this paper we visualize what the deeper layers of a ScatterNet are sensitive to using a ‘DeScatterNet’. We show that the higher orders of ScatterNets are sensitive to complex, edge-like patterns (checker-boards and rippled edges). These complex patterns may be useful for texture classification, but are quite dissimilar from the patterns visualized in second and third layers of Convolutional Neural Networks (CNNs) – the current state of the art Image Classifiers. We propose that this may be the source of the current gaps in performance between ScatterNets and CNNs (83% vs 93% on CIFAR-10 for ScatterNet+SVM vs ResNet). We then use these visualization tools to propose possible enhancements to the ScatterNet design, which show they have the power to extract features more closely resembling CNNs, while still being well-defined and having the invariance properties fundamental to ScatterNets. |
| ScatterNet Hybrid Deep Learning (SHDL) |
The paper proposes the ScatterNet Hybrid Deep Learning (SHDL) network that extracts invariant and discriminative image representations for object recognition. SHDL framework is constructed with a multi-layer ScatterNet front-end, an unsupervised learning middle, and a supervised learning back-end module. Each layer of the SHDL network is automatically designed as an explicit optimization problem leading to an optimal deep learning architecture with improved computational performance as compared to the more usual deep network architectures. SHDL network produces the state-of-the-art classification performance against unsupervised and semi-supervised learning (GANs) on two image datasets. Advantages of the SHDL network over supervised methods (NIN, VGG) are also demonstrated with experiments performed on training datasets of reduced size. |
| Scatterplot Smoothing | In statistics, several scatterplot smoothing methods are available to fit a function through the points of a scatterplot to best represent the relationship between the variables. Scatterplots may be smoothed by fitting a line to the data points in a diagram. This line attempts to display the non-random component of the association between the variables in a 2D scatter plot. Smoothing attempts to separate the non-random behaviour in the data from the random fluctuations, removing or reducing these fluctuations, and allows prediction of the response based value of the explanatory variable. |
| Scene Text Editor using Font Adaptive Neural Network (STEFANN) |
Textual information in a captured scene play important role in scene interpretation and decision making. Pieces of dedicated research work are going on to detect and recognize textual data accurately in images. Though there exist methods that can successfully detect complex text regions present in a scene, to the best of our knowledge there is no work to modify the textual information in an image. This paper deals with a simple text editor that can edit/modify the textual part in an image. Apart from error correction in the text part of the image, this work can directly increase the reusability of images drastically. In this work, at first, we focus on the problem to generate unobserved characters with the similar font and color of an observed text character present in a natural scene with minimum user intervention. To generate the characters, we propose a multi-input neural network that adapts the font-characteristics of a given characters (source), and generate desired characters (target) with similar font features. We also propose a network that transfers color from source to target character without any visible distortion. Next, we place the generated character in a word for its modification maintaining the visual consistency with the other characters in the word. The proposed method is a unified platform that can work like a simple text editor and edit texts in images. We tested our methodology on popular ICDAR 2011 and ICDAR 2013 datasets and results are reported here. |
| SceneFlowFields++ | State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation. Avoiding strong assumptions on the domain or the problem yields a more robust algorithm. This algorithm is fast because we avoid explicit regularization during matching, which allows an efficient computation. Using image information from multiple time steps and explicit visibility prediction based on previous results, we achieve competitive performances on different data sets. Our contributions and results are evaluated in comparative experiments. Overall, we present an accurate scene flow algorithm that is faster and more generic than any individual benchmark leader. |
| Scene-LSTM | We develop a human movement trajectory prediction system that incorporates the scene information (Scene-LSTM) as well as human movement trajectories (Pedestrian movement LSTM) in the prediction process within static crowded scenes. We superimpose a two-level grid structure (scene is divided into grid cells each modeled by a scene-LSTM, which are further divided into smaller sub-grids for finer spatial granularity) and explore common human trajectories occurring in the grid cell (e.g., making a right or left turn onto sidewalks coming out of an alley; or standing still at bus/train stops). Two coupled LSTM networks, Pedestrian movement LSTMs (one per target) and the corresponding Scene-LSTMs (one per grid-cell) are trained simultaneously to predict the next movements. We show that such common path information greatly influences prediction of future movement. We further design a scene data filter that holds important non-linear movement information. The scene data filter allows us to select the relevant parts of the information from the grid cell’s memory relative to a target’s state. We evaluate and compare two versions of our method with the Linear and several existing LSTM-based methods on five crowded video sequences from the UCY [1] and ETH [2] datasets. The results show that our method reduces the location displacement errors compared to related methods and specifically about 80% reduction compared to social interaction methods. |
| SchedNet | Many real-world reinforcement learning tasks require multiple agents to make sequential decisions under the agents’ interaction, where well-coordinated actions among the agents are crucial to achieve the target goal better at these tasks. One way to accelerate the coordination effect is to enable multiple agents to communicate with each other in a distributed manner and behave as a group. In this paper, we study a practical scenario when (i) the communication bandwidth is limited and (ii) the agents share the communication medium so that only a restricted number of agents are able to simultaneously use the medium, as in the state-of-the-art wireless networking standards. This calls for a certain form of communication scheduling. In that regard, we propose a multi-agent deep reinforcement learning framework, called SchedNet, in which agents learn how to schedule themselves, how to encode the messages, and how to select actions based on received messages. SchedNet is capable of deciding which agents should be entitled to broadcasting their (encoded) messages, by learning the importance of each agent’s partially observed information. We evaluate SchedNet against multiple baselines under two different applications, namely, cooperative communication and navigation, and predator-prey. Our experiments show a non-negligible performance gap between SchedNet and other mechanisms such as the ones without communication and with vanilla scheduling methods, e.g., round robin, ranging from 32% to 43%. |
| Scheduled Auxiliary Control (SAC-X) |
We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors – from scratch – in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL. The key idea behind our method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment – enabling it to excel at sparse reward RL. Our experiments in several challenging robotic manipulation settings demonstrate the power of our approach. |
| Scheduling Theory | A branch of applied mathematics (a division of operations research) concerned with mathematical formulations and solution methods of problems of optimal ordering and coordination in time of certain operations. Scheduling theory includes questions on the development of optimal schedules (Gantt charts, graphs) for performing finite (or repetitive) sets of operations. The area of application of results in scheduling theory include management, production, transportation, computer systems, construction, etc. The problems that scheduling theory deals with are usually formulated as optimization problems for a process of processing a finite set of jobs in a system with limited resources. A finite set of jobs is what distinguishes scheduling models from similar models in queueing theory, where basically infinite flows of activities are considered. In all other respects the starting points of the two theories are close. In scheduling theory, the time of arrival for every job into the system is specified. Within the system the job has to pass several processing stages, depending on the conditions of the problem. For every stage, feasible sets of resources are given, as well as the processing time depending on the resources used. The possibility of interruptions in the processing of certain jobs (so-called pre-emptions) can also be stipulated. Constraints on the processing sequence are usually described by a transitive anti-reflexive binary relation. Algorithms for the evaluation of characteristics of large partially ordered sets of jobs constitute the essence of the part of scheduling theory called network analysis (cf. Network model; Network planning). Sometimes, in scheduling models durations of re-adjustments are specified that are necessary when one job in process is replaced by another, as well as certain other conditions. |
| Schelling’s Model of Segregation | In 1971, the American economist Thomas Schelling created an agent-based model that might help explain why segregation is so difficult to combat. His model of segregation showed that even when individuals (or ‘agents’) didn’t mind being surrounded or living by agents of a different race, they would still choose to segregate themselves from other agents over time! Although the model is quite simple, it gives a fascinating look at how individuals might self-segregate, even when they have no explicit desire to do so. |
| SciBERT | Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained contextualized embedding model based on BERT (Devlin et al., 2018) to address the lack of high-quality, large-scale labeled scientific data. SciBERT leverages unsupervised pretraining on a large multi-domain corpus of scientific publications to improve performance on downstream scientific NLP tasks. We evaluate on a suite of tasks including sequence tagging, sentence classification and dependency parsing, with datasets from a variety of scientific domains. We demonstrate statistically significant improvements over BERT and achieve new state-of-the-art results on several of these tasks. |
| Scientific Data Mining | Scientific data mining is defined as data mining applied to scientific problems, rather than database marketing, finance, or business-driven applications. Scientific data mining distinguishes itself in the sense that the nature of the datasets is often very different from traditional marketdriven data mining applications. The datasets now might involve vast amounts of precise and continuous data, and accounting for underlying system nonlinearities can be extremely challenging from a machine learning point of view. |
| Scientific Information Extractor (SciIE) |
We introduce a multi-task setup of identifying and classifying entities, relations, and coreference clusters in scientific articles. We create SciERC, a dataset that includes annotations for all three tasks and develop a unified framework called Scientific Information Extractor (SciIE) for with shared span representations. The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links. Experiments show that our multi-task model outperforms previous models in scientific information extraction without using any domain-specific features. We further show that the framework supports construction of a scientific knowledge graph, which we use to analyze information in scientific literature. |
| scikit | scikit-learn: Machine Learning in Python · Simple and efficient tools for data mining and data analysis · Accessible to everybody, and reusable in various contexts · Built on NumPy, SciPy, and matplotlib · Open source, commercially usable – BSD license |
| Scikit-Multiflow | Scikit-multiflow is a multi-output/multi-label and stream data mining framework for the Python programming language. Conceived to serve as a platform to encourage democratization of stream learning research, it provides multiple state of the art methods for stream learning, stream generators and evaluators. scikit-multiflow builds upon popular open source frameworks including scikit-learn, MOA and MEKA. Development follows the FOSS principles and quality is enforced by complying with PEP8 guidelines and using continuous integration and automatic testing. Scikit-Multiflow: A Multi-output Streaming Framework |
| SciTokens | The management of security credentials (e.g., passwords, secret keys) for computational science workflows is a burden for scientists and information security officers. Problems with credentials (e.g., expiration, privilege mismatch) cause workflows to fail to fetch needed input data or store valuable scientific results, distracting scientists from their research by requiring them to diagnose the problems, re-run their computations, and wait longer for their results. In this paper, we introduce SciTokens, open source software to help scientists manage their security credentials more reliably and securely. We describe the SciTokens system architecture, design, and implementation addressing use cases from the Laser Interferometer Gravitational-Wave Observatory (LIGO) Scientific Collaboration and the Large Synoptic Survey Telescope (LSST) projects. We also present our integration with widely-used software that supports distributed scientific computing, including HTCondor, CVMFS, and XrootD. SciTokens uses IETF-standard OAuth tokens for capability-based secure access to remote scientific data. The access tokens convey the specific authorizations needed by the workflows, rather than general-purpose authentication impersonation credentials, to address the risks of scientific workflows running on distributed infrastructure including NSF resources (e.g., LIGO Data Grid, Open Science Grid, XSEDE) and public clouds (e.g., Amazon Web Services, Google Cloud, Microsoft Azure). By improving the interoperability and security of scientific workflows, SciTokens 1) enables use of distributed computing for scientific domains that require greater data protection and 2) enables use of more widely distributed computing resources by reducing the risk of credential abuse on remote systems. |
| Score Function | In statistics, the score, score function, efficient score or informant indicates how sensitively a likelihood function L(theta,X) depends on its parameter theta. Explicitly, the score for theta is the gradient of the log-likelihood with respect to theta. The score plays an important role in several aspects of inference. For example: · in formulating a test statistic for a locally most powerful test; · in approximating the error in a maximum likelihood estimate; · in demonstrating the asymptotic sufficiency of a maximum likelihood estimate; · in the formulation of confidence intervals; · in demonstrations of the Cramér-Rao inequality. The score function also plays an important role in computational statistics, as it can play a part in the computation of maximum likelihood estimates. |
| Scoring Rule | In decision theory, a score function, or scoring rule, measures the accuracy of probabilistic predictions. It is applicable to tasks in which predictions must assign probabilities to a set of mutually exclusive discrete outcomes. The set of possible outcomes can be either binary or categorical in nature, and the probabilities assigned to this set of outcomes must sum to one (where each individual probability is in the range of 0 to 1). A score can be thought of as either a measure of the “calibration” of a set of probabilistic predictions, or as a “cost function” or “loss function”. If a cost is levied in proportion to a proper scoring rule, the minimal expected cost corresponds to reporting the true set of probabilities. Proper scoring rules are used in meteorology, finance, and pattern classification where a forecaster or algorithm will attempt to minimize the average score to yield refined, calibrated probabilities (i.e. accurate probabilities). Various scoring rules have also been used to assess the predictive accuracy of football forecast models. |
| Scott-Knott | Scott-Knott is an hierarchical clustering algorithm used in the application of ANOVA, when the researcher is comparing treatment means, with a very important characteristic: it does not present any overlapping in its grouping results. We wrote a code, in R, that performs this algorithm starting from vectors, matrix, data.frame, aov or aov.list objects. The results are presented with letters representing groups, as well as through graphics using different colors to differentiate distinct groups. This R package, named ScottKnott is the main topic of this article. ScottKnott,ScottKnottESD |
| SCOUT | Finding the right cloud configuration for workloads is an essential step to ensure good performance and contain running costs. A poor choice of cloud configuration decreases application performance and increases running cost significantly. While Bayesian Optimization is effective and applicable to any workloads, it is fragile because performance and workload are hard to model (to predict). In this paper, we propose a novel method, SCOUT. The central insight of SCOUT is that using prior measurements, even those for different workloads, improves search performance and reduces search cost. At its core, SCOUT extracts search hints (inference of resource requirements) from low-level performance metrics. Such hints enable SCOUT to navigate through the search space more efficiently—only spotlight region will be searched. We evaluate SCOUT with 107 workloads on Apache Hadoop and Spark. The experimental results demonstrate that our approach finds better cloud configurations with a lower search cost than state of the art methods. Based on this work, we conclude that (i) low-level performance information is necessary for finding the right cloud configuration in an effective, efficient and reliable way, and (ii) a search method can be guided by historical data, thereby reducing cost and improving performance. |
| ScoutBot | ScoutBot is a dialogue interface to physical and simulated robots that supports collaborative exploration of environments. The demonstration will allow users to issue unconstrained spoken language commands to ScoutBot. ScoutBot will prompt for clarification if the user’s instruction needs additional input. It is trained on human-robot dialogue collected from Wizard-of-Oz experiments, where robot responses were initiated by a human wizard in previous interactions. The demonstration will show a simulated ground robot (Clearpath Jackal) in a simulated environment supported by ROS (Robot Operating System). |
| Scree Plot | A scree plot is a graphical display of the variance of each component in the dataset which is used to determine how many components should be retained in order to explain a high percentage of the variation in the data. The plot shows the variance for the first component and then for the subsequent components, it shows the additional variance that each component is adding. |
| ScreenerNet | We propose to learn a curriculum or a syllabus for supervised learning with deep neural networks. Specifically, we learn weights for each sample in training by an attached neural network, called ScreenerNet, to the original network and jointly train them in an end-to-end fashion. We show the networks augmented with our ScreenerNet achieve early convergence with better accuracy than the state-of-the-art rule-based curricular learning methods in extensive experiments using three popular vision datasets including MNIST, CIFAR10 and Pascal VOC2012, and a Cartpole task using Deep Q-learning. |
| SCvx | This paper presents the SCvx algorithm, a successive convexification algorithm designed to solve non-convex optimal control problems with global convergence and superlinear convergence-rate guarantees. The proposed algorithm handles nonlinear dynamics and non-convex state and control constraints by linearizing them about the solution of the previous iterate, and solving the resulting convex subproblem to obtain a solution for the current iterate. Additionally, the algorithm incorporates several safe-guarding techniques into each convex subproblem, employing virtual controls and virtual buffer zones to avoid artificial infeasibility, and a trust region to avoid artificial unboundedness. The procedure is repeated in succession, thus turning a difficult non-convex optimal control problem into a sequence of numerically tractable convex subproblems. Using fast and reliable Interior Point Method (IPM) solvers, the convex subproblems can be computed quickly, making the SCvx algorithm well suited for real-time applications. Analysis is presented to show that the algorithm converges both globally and superlinearly, guaranteeing the local optimality of the original problem. The superlinear convergence is obtained by exploiting the structure of optimal control problems, showcasing the superior convergence rate that can be obtained by leveraging specific problem properties when compared to generic nonlinear programming methods. Numerical simulations are performed for an illustrative non-convex quad-rotor motion planning example problem, and corresponding results obtained using Sequential Quadratic Programming (SQP) solver are provided for comparison. Our results show that the convergence rate of the SCvx algorithm is indeed superlinear, and surpasses that of the SQP-based method by converging in less than half the number of iterations. |
| SE3-Nets | We introduce SE3-Nets, which are deep networks designed to model rigid body motion from raw point cloud data. Based only on pairs of depth images along with an action vector and point wise data associations, SE3-Nets learn to segment effected object parts and predict their motion resulting from the applied force. Rather than learning point wise flow vectors, SE3-Nets predict SE3 transformations for different parts of the scene. Using simulated depth data of a table top scene and a robot manipulator, we show that the structure underlying SE3-Nets enables them to generate a far more consistent prediction of object motion than traditional flow based networks. |
| Seaborn | Seaborn is a Python visualization library based on matplotlib. It provides a high-level interface for drawing attractive statistical graphics. |
| SEALion | We present SEALion: an extensible framework for privacy-preserving machine learning with homomorphic encryption. It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data. The framework consists of two layers: the first is built upon TensorFlow and SEAL and exposes standard algebra and deep learning primitives; the second implements a Keras-like syntax for training and inference with neural networks. Given a required level of security, a user is abstracted from the details of the encoding and the encryption scheme, allowing quick prototyping. We present two applications that exemplifying the extensibility of our proposal, which are also of independent interest: i) improving efficiency of neural network inference by an activity sparsifier and ii) transfer learning by querying a server-side Variational AutoEncoder that can handle encrypted data. |
| Search Partition Analysis (SPAN) |
spanr |
| Search Session Markov Decision Process (SSMDP) |
In e-commerce platforms such as Amazon and TaoBao, ranking items in a search session is a typical multi-step decision-making problem. Learning to rank (LTR) methods have been widely applied to ranking problems. However, such methods often consider different ranking steps in a session to be independent, which conversely may be highly correlated to each other. For better utilizing the correlation between different ranking steps, in this paper, we propose to use reinforcement learning (RL) to learn an optimal ranking policy which maximizes the expected accumulative rewards in a search session. Firstly, we formally define the concept of search session Markov decision process (SSMDP) to formulate the multi-step ranking problem. Secondly, we analyze the property of SSMDP and theoretically prove the necessity of maximizing accumulative rewards. Lastly, we propose a novel policy gradient algorithm for learning an optimal ranking policy, which is able to deal with the problem of high reward variance and unbalanced reward distribution of an SSMDP. Experiments are conducted in simulation and TaoBao search engine. The results demonstrate that our algorithm performs much better than online LTR methods, with more than 40% and 30% growth of total transaction amount in the simulation and the real application, respectively. |
| SEARNN | We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the ‘learning to search’ (L2S) approach to structured prediction. RNNs have been widely successful in structured prediction applications such as machine translation or parsing, and are commonly trained using maximum likelihood estimation (MLE). Unfortunately, this training loss is not always an appropriate surrogate for the test error: by only maximizing the ground truth probability, it fails to exploit the wealth of information offered by structured losses. Further, it introduces discrepancies between training and predicting (such as exposure bias) that may hurt test performance. Instead, SEARNN leverages test-alike search space exploration to introduce global-local losses that are closer to the test error. We demonstrate improved performance over MLE on three different tasks: OCR, spelling correction and text chunking. Finally, we propose a subsampling strategy to enable SEARNN to scale to large vocabulary sizes. |
| Seasonal ARIMA (SARIMA) |
Often time series possess a seasonal component that repeats every s observations. For monthly observations s = 12 (12 in 1 year), for quarterly observations s = 4 (4 in 1 year). In order to deal with seasonality, ARIMA processes have been generalized: SARIMA models have then been formulated. |
| Seasonal Decomposition of Time Series by Loess (STL) |
Decompose a time series into seasonal, trend and irregular components using loess. |
| Seasonal Hybrid ESD (S-H-ESD) |
The primary algorithm, Seasonal Hybrid ESD (S-H-ESD), builds upon the Generalized ESD test for detecting anomalies. S-H-ESD can be used to detect both global and local anomalies. This is achieved by employing time series decomposition and using robust statistical metrics, viz., median together with ESD. In addition, for long time series such as 6 months of minutely data, the algorithm employs piecewise approximation. This is rooted to the fact that trend extraction in the presence of anomalies is non-trivial for anomaly detection. AnomalyDetection |
| Second-Level Global Sensitivity Analysis (GSA2) |
Global sensitivity analysis (GSA) of numerical simulators aims at studying the global impact of the input uncertainties on the output. To perform the GSA, statistical tools based on inputs/output dependence measures are commonly used. We focus here on dependence measures based on reproducing kernel Hilbert spaces: the Hilbert-Schmidt Independence Criterion denoted HSIC. Sometimes, the probability distributions modeling the uncertainty of inputs may be themselves uncertain and it is important to quantify the global impact of this uncertainty on GSA results. We call it here the second-level global sensitivity analysis (GSA2). However, GSA2, when performed with a double Monte Carlo loop, requires a large number of model evaluations which is intractable with CPU time expensive simulators. To cope with this limitation, we propose a new statistical methodology based on a single Monte Carlo loop with a limited calculation budget. Firstly, we build a unique sample of inputs from a well chosen probability distribution and the associated code outputs are computed. From this inputs/output sample, we perform GSA for various assumed probability distributions of inputs by using weighted HSIC measures estimators. Statistical properties of these weighted esti-mators are demonstrated. Finally, we define 2 nd-level HSIC-based measures between the probability distributions of inputs and GSA results, which constitute GSA2 indices. The efficiency of our GSA2 methodology is illustrated on an analytical example, thereby comparing several technical options. Finally, an application to a test case simulating a severe accidental scenario on nuclear reactor is provided. |
| Second-Order Convolutional Neural Networks | Convolutional Neural Networks (CNNs) have been successfully applied to many computer vision tasks, such as image classification. By performing linear combinations and element-wise nonlinear operations, these networks can be thought of as extracting solely first-order information from an input image. In the past, however, second-order statistics computed from handcrafted features, e.g., covariances, have proven highly effective in diverse recognition tasks. In this paper, we introduce a novel class of CNNs that exploit second-order statistics. To this end, we design a series of new layers that (i) extract a covariance matrix from convolutional activations, (ii) compute a parametric, second-order transformation of a matrix, and (iii) perform a parametric vectorization of a matrix. These operations can be assembled to form a Covariance Descriptor Unit (CDU), which replaces the fully-connected layers of standard CNNs. Our experiments demonstrate the benefits of our new architecture, which outperform the first-order CNNs, while relying on up to 90% fewer parameters. |
| Second-Order Pooling | |
| SECTOR | When searching for information, a human reader first glances over a document, spots relevant sections and then focuses on a few sentences for resolving her intention. However, the high variance of document structure complicates to identify the salient topic of a given section at a glance. To tackle this challenge, we present SECTOR, a model to support machine reading systems by segmenting documents into coherent sections and assigning topic labels to each section. Our deep neural network architecture learns a latent topic embedding over the course of a document. This can be leveraged to classify local topics from plain text and segment a document at topic shifts. In addition, we contribute WikiSection, a publicly available dataset with 242k labeled sections in English and German from two distinct domains: diseases and cities. From our extensive evaluation of 20 architectures, we report a highest score of 71.6% F1 for the segmentation and classification of 30 topics from the English city domain, scored by our SECTOR LSTM model with bloom filter embeddings and bidirectional segmentation. This is a significant improvement of 29.5 points F1 compared to state-of-the-art CNN classifiers with baseline segmentation. |
| Secure Federated Learning | Today’s AI still faces two major challenges. One is that in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these challenges: secure federated learning. Beyond the federated learning framework first proposed by Google in 2016, we introduce a comprehensive secure federated learning framework, which includes horizontal federated learning, vertical federated learning and federated transfer learning. We provide definitions, architectures and applications for the federated learning framework, and provide a comprehensive survey of existing works on this subject. In addition, we propose building data networks among organizations based on federated mechanisms as an effective solution to allow knowledge to be shared without compromising user privacy. |
| SecureBoost | The protection of user privacy is an important concern in machine learning, as evidenced by the rolling out of the General Data Protection Regulation (GDPR) in the European Union (EU) in May 2018. The GDPR is designed to give users more control over their personal data, which motivates us to explore machine learning frameworks with data sharing without violating user privacy. To meet this goal, in this paper, we propose a novel lossless privacy-preserving tree-boosting system known as SecureBoost in the setting of federated learning. This federated-learning system allows a learning process to be jointly conducted over multiple parties with partially common user samples but different feature sets, which corresponds to a vertically partitioned virtual data set. An advantage of SecureBoost is that it provides the same level of accuracy as the non-privacy-preserving approach while at the same time, reveal no information of each private data provider. We theoretically prove that the SecureBoost framework is as accurate as other non-federated gradient tree-boosting algorithms that bring the data into one place. In addition, along with a proof of security, we discuss what would be required to make the protocols completely secure. |
| SecureStreams | The growing adoption of distributed data processing frameworks in a wide diversity of application domains challenges end-to-end integration of properties like security, in particular when considering deployments in the context of large-scale clusters or multi-tenant Cloud infrastructures. This paper therefore introduces SecureStreams, a reactive middleware framework to deploy and process secure streams at scale. Its design combines the high-level reactive dataflow programming paradigm with Intel’s low-level software guard extensions (SGX) in order to guarantee privacy and integrity of the processed data. The experimental results of SecureStreams are promising: while offering a fluent scripting language based on Lua, our middleware delivers high processing throughput, thus enabling developers to implement secure processing pipelines in just few lines of code. |
| Sedano | We present Sedano, a system for processing and indexing a continuous stream of business-related news. Sedano defines pipelines whose stages analyze and enrich news items (e.g., newspaper articles and press releases). News data coming from several content sources are stored, processed and then indexed in order to be consumed by Atoka, our business intelligence product. Atoka users can retrieve news about specific companies, filtering according to various facets. Sedano features both an entity-linking phase, which finds mentions of companies in news, and a classification phase, which classifies news according to a set of business events. Its flexible architecture allows Sedano to be deployed on commodity machines while being scalable and fault-tolerant. |
| Seemingly Unrelated Regression (SUR) |
In econometrics, the seemingly unrelated regressions (SUR) or seemingly unrelated regression equations (SURE) model, proposed by Arnold Zellner in (1962), is a generalization of a linear regression model that consists of several regression equations, each having its own dependent variable and potentially different sets of exogenous explanatory variables. Each equation is a valid linear regression on its own and can be estimated separately, which is why the system is called seemingly unrelated, although some authors suggest that the term seemingly related would be more appropriate, since the error terms are assumed to be correlated across the equations. The model can be estimated equation-by-equation using standard ordinary least squares (OLS). Such estimates are consistent, however generally not as efficient as the SUR method, which amounts to feasible generalized least squares with a specific form of the variance-covariance matrix. Two important cases when SUR is in fact equivalent to OLS are when the error terms are in fact uncorrelated between the equations (so that they are truly unrelated) and when each equation contains exactly the same set of regressors on the right-hand-side. The SUR model can be viewed as either the simplification of the general linear model where certain coefficients in matrix B {\displaystyle \mathrm {B} } \Beta are restricted to be equal to zero, or as the generalization of the general linear model where the regressors on the right-hand-side are allowed to be different in each equation. The SUR model can be further generalized into the simultaneous equations model, where the right-hand side regressors are allowed to be the endogenous variables as well. |
| Seesaw-Net | In this paper, we are interested in boosting the representation capability of convolution neural networks which utilizing the inverted residual structure. Based on the success of Inverted Residual structure[Sandler et al. 2018] and Interleaved Low-Rank Group Convolutions[Sun et al. 2018], we rethink this two pattern of neural network structure, rather than NAS(Neural architecture search) method[Zoph and Le 2017; Pham et al. 2018; Liu et al. 2018b], we introduce uneven point-wise group convolution, which provide a novel search space for designing basic blocks to obtain better trade-off between representation capability and computational cost. Meanwhile, we propose two novel information flow patterns that will enable cross-group information flow for multiple group convolution layers with and without any channel permute/shuffle operation. Dense experiments on image classification task show that our proposed model, named Seesaw-Net, achieves state-of-the-art (SOTA) performance with limited computation and memory cost. Our code will be open-source and available together with pre-trained models. |
| Seglearn | Seglearn is an open-source python package for machine learning time series or sequences using a sliding window segmentation approach. The implementation provides a flexible pipeline for tackling classification, regression, and forecasting problems with multivariate sequence and contextual data. This package is compatible with scikit-learn and is listed under scikit-learn Related Projects. The package depends on numpy, scipy, and scikit-learn. Seglearn is distributed under the BSD 3-Clause License. Documentation includes a detailed API description, user guide, and examples. Unit tests provide a high degree of code coverage. |
| Segment Unannotated image Structure using Adversarial Network (SUSAN) |
Segmentation of magnetic resonance (MR) images is a fundamental step in many medical imaging-based applications. The recent implementation of deep convolutional neural networks (CNNs) in image processing has been shown to have significant impacts on medical image segmentation. Network training of segmentation CNNs typically requires images and paired annotation data representing pixel-wise tissue labels referred to as masks. However, the supervised training of highly efficient CNNs with deeper structure and more network parameters requires a large number of training images and paired tissue masks. Thus, there is great need to develop a generalized CNN-based segmentation method which would be applicable for a wide variety of MR image datasets with different tissue contrasts. The purpose of this study was to develop and evaluate a generalized CNN-based method for fully-automated segmentation of different MR image datasets using a single set of annotated training data. A technique called cycle-consistent generative adversarial network (CycleGAN) is applied as the core of the proposed method to perform image-to-image translation between MR image datasets with different tissue contrasts. A joint segmentation network is incorporated into the adversarial network to obtain additional segmentation functionality. The proposed method was evaluated for segmenting bone and cartilage on two clinical knee MR image datasets acquired at our institution using only a single set of annotated data from a publicly available knee MR image dataset. The new technique may further improve the applicability and efficiency of CNN-based segmentation of medical images while eliminating the need for large amounts of annotated training data. |
| Segmental Recurrent Neural Network (SRNN) |
We introduce segmental recurrent neural networks (SRNNs) which define, given an input sequence, a joint probability distribution over segmentations of the input and labelings of the segments. Representations of the input segments (i.e., contiguous subsequences of the input) are computed by encoding their constituent tokens using bidirectional recurrent neural nets, and these ‘segment embeddings’ are used to define compatibility scores with output labels. These local compatibility scores are integrated using a global semi-Markov conditional random field. Both fully supervised training – in which segment boundaries and labels are observed – as well as partially supervised training – in which segment boundaries are latent – are straightforward. Experiments on handwriting recognition and joint Chinese word segmentation/POS tagging show that, compared to models that do not explicitly represent segments such as BIO tagging schemes and connectionist temporal classification (CTC), SRNNs obtain substantially higher accuracies. |
| Segmentation-Based Matrix Factorization (SPMF) |
The traditional social recommendation algorithm ignores the following fact: the preferences of users with trust relationships are not necessarily similar, and the consideration of user preference similarity should be limited to specific areas. A social trust and preference segmentation-based matrix factorization (SPMF) recommendation system is proposed to solve the above-mentioned problems. Experimental results based on the Ciao and Epinions datasets show that the accuracy of the SPMF algorithm is significantly higher than that of some state-of-the-art recommendation algorithms. The proposed SPMF algorithm is a more accurate and effective recommendation algorithm based on distinguishing the difference of trust relations and preference domain, which can support commercial activities such as product marketing. |
| Segmented Linear Regression | Segmented linear regression with two segments separated by a breakpoint can be useful to quantify an abrupt change of the response function (Yr) of a varying influential factor (x). The breakpoint can be interpreted as a critical, safe, or threshold value beyond or below which (un)desired effects occur. The breakpoint can be important in decision making. cowbell |
| Segmented Regression | Segmented regression, also known as piecewise regression or ‘broken-stick regression’, is a method in regression analysis in which the independent variable is partitioned into intervals and a separate line segment is fit to each interval. Segmented regression analysis can also be performed on multivariate data by partitioning the various independent variables. Segmented regression is useful when the independent variables, clustered into different groups, exhibit different relationships between the variables in these regions. The boundaries between the segments are breakpoints. Segmented linear regression is segmented regression whereby the relations in the intervals are obtained by linear regression. segmented |
| Segment-Enhance-Inpaint Generative Adversarial Network (SEIGAN) |
We present a novel approach to image manipulation and understanding by simultaneously learning to segment object masks, paste objects to another background image, and remove them from original images. For this purpose, we develop a novel generative model for compositional image generation, SEIGAN (Segment-Enhance-Inpaint Generative Adversarial Network), which learns these three operations together in an adversarial architecture with additional cycle consistency losses. To train, SEIGAN needs only bounding box supervision and does not require pairing or ground truth masks. SEIGAN produces better generated images (evaluated by human assessors) than other approaches and produces high-quality segmentation masks, improving over other adversarially trained approaches and getting closer to the results of fully supervised training. |
| Segment-level POlariTy annotations (SPOT) |
We consider the task of fine-grained sentiment analysis from the perspective of multiple instance learning (MIL). Our neural model is trained on document sentiment labels, and learns to predict the sentiment of text segments, i.e. sentences or elementary discourse units (EDUs), without segment-level supervision. We introduce an attention-based polarity scoring method for identifying positive and negative text snippets and a new dataset which we call SPOT (as shorthand for Segment-level POlariTy annotations) for evaluating MIL-style sentiment models like ours. Experimental results demonstrate superior performance against multiple baselines, whereas a judgement elicitation study shows that EDU-level opinion extraction produces more informative summaries than sentence-based alternatives. |
| SegReg | In statistics and data analysis the application software SegReg is a free and user-friendly tool for linear segmented regression analysis to determine the breakpoint where the relation between the dependent variable and the independent variable changes abruptly. Originally the method was developed for the analysis of the influence of soil salinity and depth of the watertable on growth of agricultural crops. However, it can be used for many other types of phenomena and relations, for example: · the change of nutrient contents in plants with time · the number of negative indicator responses at 30% upstream riparian harvest · phosphorus and flow duration on the Saline River |
| Segregation Network | The problem of multiple class novelty detection is gaining increasing importance due to the large availability of multimedia data and the increasing requirement of the classification models to work in an open set scenario. To this end, novelty detection tries to answer this important question: given a test example should we even try to classify it? In this work, we design a novel deep learning framework, termed Segregation Network, which is trained using the mixup technique. We construct interpolated points using convex combinations of pairs of training data and use our novel loss function for prediction of its constituent classes. During testing, for each input query, mixed samples with the known class prototypes are generated and passed through the proposed network. The output of the network reveals the constituent classes which can be used to determine whether the incoming data is from the known class set or not. Our algorithm is trained using just the data from the known classes and does not require any auxiliary dataset or attributes. Extensive evaluation on two benchmark datasets namely Caltech-256 and Stanford Dogs and comparison with the state-of-the-art justifies the effectiveness of the proposed framework. |
| Seldon | Seldon is an open-source predictive analytics platform. Our proven machine learning algorithms and highly scalable platform serve recommendations to hundreds of millions of people across some of the world’s leading media and e-commerce brands. Seldon VM contains the entire platform pre-configured in a virtual machine for you to get started quickly, to test Seldon with your service data and a movie recommender demo. |
| SelectionNet | Recent years have witnessed growing interests in designing efficient neural networks and neural architecture search (NAS). Although remarkable efficiency and accuracy have been achieved, existing expert designed and NAS models neglect that input instances are of varying complexity thus different amount of computation is required. Therefore, inference with a fixed model that processes all instances through the same transformations would waste plenty of computational resources. Customizing the model capacity in an instance-aware manner is highly demanded. In this paper, we introduce a novel network ISBNet to address this issue, which supports efficient instance-level inference by selectively bypassing transformation branches of infinitesimal importance weight. We also propose lightweight hypernetworks SelectionNet to generate these importance weights instance-wisely. Extensive experiments have been conducted to evaluate the efficiency of ISBNet and the results show that ISBNet achieves extremely efficient inference comparing to existing networks. For example, ISBNet takes only 12.45% parameters and 45.79% FLOPs of the state-of-the-art efficient network ShuffleNetV2 with comparable accuracy. |
| Selective Clustering Annotated Using Modes of Projections (SCAMP) |
Selective clustering annotated using modes of projections (SCAMP) is a new clustering algorithm for data in $\mathbb{R}^p$. SCAMP is motivated from the point of view of non-parametric mixture modeling. Rather than maximizing a classification likelihood to determine cluster assignments, SCAMP casts clustering as a search and selection problem. One consequence of this problem formulation is that the number of clusters is $\textbf{not}$ a SCAMP tuning parameter. The search phase of SCAMP consists of finding sub-collections of the data matrix, called candidate clusters, that obey shape constraints along each coordinate projection. An extension of the dip test of Hartigan and Hartigan (1985) is developed to assist the search. Selection occurs by scoring each candidate cluster with a preference function that quantifies prior belief about the mixture composition. Clustering proceeds by selecting candidates to maximize their total preference score. SCAMP concludes by annotating each selected cluster with labels that describe how cluster-level statistics compare to certain dataset-level quantities. SCAMP can be run multiple times on a single data matrix. Comparison of annotations obtained across iterations provides a measure of clustering uncertainty. Simulation studies and applications to real data are considered. A C++ implementation with R interface is $\href{https://…/scamp}{available\ online}$. |
| Selective Feature Connection Mechanism (SFCM) |
Different layers of deep convolutional neural networks(CNN) can encode different-level information. High-layer features always contain more semantic information, and low-layer features contain more detail information. However, low-layer features suffer from the background clutter and semantic ambiguity. During visual recognition, the feature combination of the low-layer and high-level features plays an important role in context modulation. Directly combining the high-layer and low-layer features, the background clutter and semantic ambiguity may be caused due to the introduction of detailed information.In this paper, we propose a general network architecture to concatenate CNN features of different layers in a simple and effective way, called Selective Feature Connection Mechanism (SFCM). Low level features are selectively linked to high-level features with an feature selector which is generated by high-level features. The proposed connection mechanism can effectively overcome the above-mentioned drawbacks. We demonstrate the effectiveness, superiority, and universal applicability of this method on many challenging computer vision tasks, such as image classification, scene text detection, and image-to-image translation. |
| Selective Kernel (SK) |
In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size of visual cortical neurons are modulated by the stimulus, which has been rarely considered in constructing CNNs. We propose a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information. A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer. Multiple SK units are stacked to a deep network termed Selective Kernel Networks (SKNets). On the ImageNet and CIFAR benchmarks, we empirically show that SKNet outperforms the existing state-of-the-art architectures with lower model complexity. Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their recpeitve field sizes according to the input. The code and models are available at https://…/SKNet. |
| Selective Kernel Network | In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size of visual cortical neurons are modulated by the stimulus, which has been rarely considered in constructing CNNs. We propose a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information. A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer. Multiple SK units are stacked to a deep network termed Selective Kernel Networks (SKNets). On the ImageNet and CIFAR benchmarks, we empirically show that SKNet outperforms the existing state-of-the-art architectures with lower model complexity. Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their recpeitve field sizes according to the input. The code and models are available at https://…/SKNet. |
| Selective Prediction | We consider a model of selective prediction, where the prediction algorithm is given a data sequence in an online fashion and asked to predict a pre-specified statistic of the upcoming data points. The algorithm is allowed to choose when to make the prediction as well as the length of the prediction window, possibly depending on the observations so far. We prove that, even without any distributional assumption on the input data stream, a large family of statistics can be estimated to non-trivial accuracy. To give one concrete example, suppose that we are given access to an arbitrary binary sequence $x_1, \ldots, x_n$ of length $n$. Our goal is to accurately predict the average observation, and we are allowed to choose the window over which the prediction is made: for some $t < n$ and $m \le n – t$, after seeing $t$ observations we predict the average of $x_{t+1}, \ldots, x_{t+m}$. We show that the expected squared error of our prediction can be bounded by $O\left(\frac{1}{\log n}\right)$, and prove a matching lower bound. This result holds for any sequence (that is not adaptive to when the prediction is made, or the predicted value), and the expectation of the error is with respect to the randomness of the prediction algorithm. Our results apply to more general statistics of a sequence of observations, and we highlight several open directions for future work. |
| SelectiveNet | We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option. Existing rejection mechanisms are based mostly on a threshold over the prediction confidence of a pre-trained network. In contrast, SelectiveNet is trained to optimize both classification (or regression) and rejection simultaneously, end-to-end. The result is a deep neural network that is optimized over the covered domain. In our experiments, we show a consistently improved risk-coverage trade-off over several well-known classification and regression datasets, thus reaching new state-of-the-art results for deep selective classification. |
| SelectNet | Supervised learning from training data with imbalanced class sizes, a commonly encountered scenario in real applications such as anomaly/fraud detection, has long been considered a significant challenge in machine learning. Motivated by recent progress in curriculum and self-paced learning, we propose to adopt a semi-supervised learning paradigm by training a deep neural network, referred to as SelectNet, to selectively add unlabelled data together with their predicted labels to the training dataset. Unlike existing techniques designed to tackle the difficulty in dealing with class imbalanced training data such as resampling, cost-sensitive learning, and margin-based learning, SelectNet provides an end-to-end approach for learning from important unlabelled data ‘in the wild’ that most likely belong to the under-sampled classes in the training data, thus gradually mitigates the imbalance in the data used for training the classifier. We demonstrate the efficacy of SelectNet through extensive numerical experiments on standard datasets in computer vision. |
| SelectScript | We introduce a new declarative language called SELECTSCRIPT. As its name suggests, it is a scripting language inspired primarily by SQL and its relational algebra. It is intended to be used for complex queries on different kinds of world models. Scripts can be dynamically generated and executed, or embedded into the code of foreign programming languages. A first interpreter was therefore developed for Python. Adapting the ideas of language-oriented programming, which enables developers to create their own domain-specific language, we developed a language stub that can be easily adapted and extended to comply with any (discrete) robotic world model or robotic simulator. We will further show how simple SELECT-statements can be used to extract any kind of valuable information in various return formats, thereby going beyond traditional SQL capabilities. Reasoning in complex environments with the SelectScript declarative language |
| Self Distillation | Convolutional neural networks have been widely deployed in various application scenarios. In order to extend the applications’ boundaries to some accuracy-crucial domains, researchers have been investigating approaches to boost accuracy through either deeper or wider network structures, which brings with them the exponential increment of the computational and storage cost, delaying the responding time. In this paper, we propose a general training framework named self distillation, which notably enhances the performance (accuracy) of convolutional neural networks through shrinking the size of the network rather than aggrandizing it. Different from traditional knowledge distillation – a knowledge transformation methodology among networks, which forces student neural networks to approximate the softmax layer outputs of pre-trained teacher neural networks, the proposed self distillation framework distills knowledge within network itself. The networks are firstly divided into several sections. Then the knowledge in the deeper portion of the networks is squeezed into the shallow ones. Experiments further prove the generalization of the proposed self distillation framework: enhancement of accuracy at average level is 2.65%, varying from 0.61% in ResNeXt as minimum to 4.07% in VGG19 as maximum. In addition, it can also provide flexibility of depth-wise scalable inference on resource-limited edge devices.Our codes will be released on github soon. |
| Self Driving Data Curation | Past. Data curation – the process of discovering, integrating, and cleaning data – is one of the oldest data management problems. Unfortunately, it is still the most time consuming and least enjoyable work of data scientists. So far, successful data curation stories are mainly ad-hoc solutions that are either domain-specific (for example, ETL rules) or task-specific (for example, entity resolution). Present. The power of current data curation solutions are not keeping up with the ever changing data ecosystem in terms of volume, velocity, variety and veracity, mainly due to the high human cost, instead of machine cost, needed for providing the ad-hoc solutions mentioned above. Meanwhile, deep learning is making strides in achieving remarkable successes in areas such as image recognition, natural language processing, and speech recognition. This is largely due to its ability to understanding features that are neither domain-specific nor task-specific. Future. Data curation solutions need to keep the pace with the fast-changing data ecosystem, where the main hope is to devise domain-agnostic and task-agnostic solutions. To this end, we start a new research project, called AutoDC, to unleash the potential of deep learning towards self-driving data curation. We will discuss how different deep learning concepts can be adapted and extended to solve various data curation problems. We showcase some low-hanging fruits about the early encounters between deep learning and data curation happening in AutoDC. We believe that the directions pointed out by this work will not only drive AutoDC towards democratizing data curation, but also serve as a cornerstone for researchers and practitioners to move to a new realm of data curation solutions. |
| Self Exciting Point Process (SEPP) |
A point process N is called self-exciting if cov(N(s,t),N(t,u))>0 for s<t<u where here, cov denotes the covariance of the two quantities. Intuitively, a process is self-exciting if the occurrence of past points makes the occurrence of future points more probable. Spatio-Temporal Modeling with R: Point process prediction for mortals |
| Self Normalizing Convolutional Neural Network (SCNN) |
Self Normalizing Neural Networks (SNN) proposed on Feed Forward Neural Networks (FNN) outperform regular FNN architectures in various machine learning tasks. Particularly in the domain of Computer Vision, the activation function Scaled Exponential Linear Units (SELU) proposed for SNNs, perform better than other non linear activations such as ReLU. The goal of SNN is to produce a normalized output for a normalized input. Established neural network architectures like feed forward networks and Convolutional Neural Networks (CNN) lack the intrinsic nature of normalizing outputs. Hence, requiring additional layers such as Batch Normalization. Despite the success of SNNs, their characteristic features on other network architectures like CNN haven’t been explored, especially in the domain of Natural Language Processing. In this paper we aim to show the effectiveness of proposed, Self Normalizing Convolutional Neural Networks (SCNN) on text classification. We analyze their performance with the standard CNN architecture used on several text classification datasets. Our experiments demonstrate that SCNN achieves comparable results to standard CNN model with significantly fewer parameters. Furthermore it also outperforms CNN with equal number of parameters. |
| Self Organising Deltoids | self-organising deltoids dimension squeezing algorithm. This is a simple algorithm that tries to find reasonable positions in m-dimensional space for a set of points in n dimensions (where m is smaller than n). It’s main usage is to visualise n-dimensional data in 2 dimensions, but any dimensionality can be choosen.The algorithm simply takes a set of points in N-dimensions, and then gradually squeezes out the excess dimensions using the errors in inter-node distances to arrange the nodes in the reduced dimensional space. |
| Self Organizing Classifier | Learning classifier systems (LCSs) are evolutionary machine learning algorithms, flexible enough to be applied to reinforcement, supervised and unsupervised learning problems with good performance. Recently, self organizing classifiers were proposed which are similar to LCSs but have the advantage that in its structured population no balance between niching and fitness pressure is necessary. However, more tests and analysis are required to verify its benefits. Here, a variation of the first algorithm is proposed which uses a parameterless self organizing map (SOM). This algorithm is applied in challenging problems such as big, noisy as well as dynamically changing continuous input-action mazes (growing and compressing mazes are included) with good performance. Moreover, a genetic operator is proposed which utilizes the topological information of the SOM’s population structure, improving the results. Thus, the first steps in structured evolutionary machine learning are shown, nonetheless, the problems faced are more difficult than the state-of-art continuous input-action multi-step ones. |
| Self Other-Modeling (SOM) |
We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must infer the other players’ hidden goals from their observed behavior in order to solve the tasks. We propose a new approach for learning in these domains: Self Other-Modeling (SOM), in which an agent uses its own policy to predict the other agent’s actions and update its belief of their hidden state in an online manner. We evaluate this approach on three different tasks and show that the agents are able to learn better policies using their estimate of the other players’ hidden states, in both cooperative and adversarial settings. |
| Self Supervised Learning | Self-supervised learning is autonomous supervised learning. It is a representation learning approach that eliminates the pre-requisite requiring humans to label data. Self-supervised learning systems extract and use the naturally available relevant context and embedded metadata as supervisory signals. |
| Self-Adaptive Discrete Particle Swarm Optimization Algorithm With Genetic Algorithm Operators (GA-DPSO) |
Compared to traditional distributed computing environments such as grids, cloud computing provides a more cost-effective way to deploy scientific workflows. Each task of a scientific workflow requires several large datasets that are located in different datacenters from the cloud computing environment, resulting in serious data transmission delays. Edge computing reduces the data transmission delays and supports the fixed storing manner for scientific workflow private datasets, but there is a bottleneck in its storage capacity. It is a challenge to combine the advantages of both edge computing and cloud computing to rationalize the data placement of scientific workflow, and optimize the data transmission time across different datacenters. Traditional data placement strategies maintain load balancing with a given number of datacenters, which results in a large data transmission time. In this study, a self-adaptive discrete particle swarm optimization algorithm with genetic algorithm operators (GA-DPSO) was proposed to optimize the data transmission time when placing data for a scientific workflow. This approach considered the characteristics of data placement combining edge computing and cloud computing. In addition, it considered the impact factors impacting transmission delay, such as the band-width between datacenters, the number of edge datacenters, and the storage capacity of edge datacenters. The crossover operator and mutation operator of the genetic algorithm were adopted to avoid the premature convergence of the traditional particle swarm optimization algorithm, which enhanced the diversity of population evolution and effectively reduced the data transmission time. The experimental results show that the data placement strategy based on GA-DPSO can effectively reduce the data transmission time during workflow execution combining edge computing and cloud computing. |
| Self-Adaptive Neuro-Fuzzy Inference System (SANFIS) |
This paper presents a self-adaptive neuro-fuzzy inference system (SANFIS) that is capable of self-adapting and self-organizing its internal structure to acquire a parsimonious rule-base for interpreting the embedded knowledge of a system from the given training data set. A connectionist topology of fuzzy basis functions with their universal approximation capability is served as a fundamental SANFIS architecture that provides an elasticity to be extended to all existing fuzzy models whose consequent could be fuzzy term sets, fuzzy singletons, or functions of linear combination of input variables. Without a priori knowledge of the distribution of the training data set, a novel mapping-constrained agglomerative clustering algorithm is devised to reveal the true cluster configuration in a single pass for an initial SANFIS construction, estimating the location and variance of each cluster. Subsequently, a fast recursive linear/nonlinear least-squares algorithm is performed to further accelerate the learning convergence and improve the system performance. Good generalization capability, fast learning convergence and compact comprehensible knowledge representation summarize the strength of SANFIS. Computer simulations for the Iris, Wisconsin breast cancer, and wine classifications show that SANFIS achieves significant improvements in terms of learning convergence, higher accuracy in recognition, and a parsimonious architecture. |
| Self-Adaptive Neurofuzzy System (SANFS) |
|
| Self-Adaptive Systems (SAS) |
Self Adaptive Software evaluates its own behavior and changes behavior when the evaluation indicates that it is not accomplishing what the software is intended to do, or when better functionality or performance is possible. |
| Self-Adaptive Visual Navigation Method (SAVN) |
Learning is an inherently continuous phenomenon. When humans learn a new task there is no explicit distinction between training and inference. After we learn a task, we keep learning about it while performing the task. What we learn and how we learn it varies during different stages of learning. Learning how to learn and adapt is a key property that enables us to generalize effortlessly to new settings. This is in contrast with conventional settings in machine learning where a trained model is frozen during inference. In this paper we study the problem of learning to learn at both training and inference time in the context of visual navigation. A fundamental challenge in navigation is generalization to unseen scenes. In this paper we propose a self-adaptive visual navigation method (SAVN) which learns to adapt to new environments without any explicit supervision. Our solution is a meta-reinforcement learning approach where an agent learns a self-supervised interaction loss that encourages effective navigation. Our experiments, performed in the AI2-THOR framework, show major improvements in both success rate and SPL for visual navigation in novel scenes. |
| Self-Adjusting Linear Network | Emerging networked systems become increasingly flexible and reconfigurable. This introduces an opportunity to adjust networked systems in a demand-aware manner, leveraging spatial and temporal locality in the workload for online optimizations. However, it also introduces a trade-off: while more frequent adjustments can improve performance, they also entail higher reconfiguration costs. This paper initiates the formal study of linear networks which self-adjust to the demand in an online manner, striking a balance between the benefits and costs of reconfigurations. We show that the underlying algorithmic problem can be seen as a distributed generalization of the classic dynamic list update problem known from self-adjusting datastructures: in a network, requests can occur between node pairs. This distributed version turns out to be significantly harder than the classical problem in generalizes. Our main results are a $\Omega(\log{n})$ lower bound on the competitive ratio, and a (distributed) online algorithm that is $O(\log{n})$-competitive if the communication requests are issued according to a linear order. |
| Self-Adversarially Learned Bayesian Sampling | Scalable Bayesian sampling is playing an important role in modern machine learning, especially in the fast-developed unsupervised-(deep)-learning models. While tremendous progresses have been achieved via scalable Bayesian sampling such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD), the generated samples are typically highly correlated. Moreover, their sample-generation processes are often criticized to be inefficient. In this paper, we propose a novel self-adversarial learning framework that automatically learns a conditional generator to mimic the behavior of a Markov kernel (transition kernel). High-quality samples can be efficiently generated by direct forward passes though a learned generator. Most importantly, the learning process adopts a self-learning paradigm, requiring no information on existing Markov kernels, e.g., knowledge of how to draw samples from them. Specifically, our framework learns to use current samples, either from the generator or pre-provided training data, to update the generator such that the generated samples progressively approach a target distribution, thus it is called self-learning. Experiments on both synthetic and real datasets verify advantages of our framework, outperforming related methods in terms of both sampling efficiency and sample quality. |
| Self-Attention Aligner (SAA) |
Self-attention network, an attention-based feedforward neural network, has recently shown the potential to replace recurrent neural networks (RNNs) in a variety of NLP tasks. However, it is not clear if the self-attention network could be a good alternative of RNNs in automatic speech recognition (ASR), which processes the longer speech sequences and may have online recognition requirements. In this paper, we present a RNN-free end-to-end model: self-attention aligner (SAA), which applies the self-attention networks to a simplified recurrent neural aligner (RNA) framework. We also propose a chunk-hopping mechanism, which enables the SAA model to encode on segmented frame chunks one after another to support online recognition. Experiments on two Mandarin ASR datasets show the replacement of RNNs by the self-attention networks yields a 8.4%-10.2% relative character error rate (CER) reduction. In addition, the chunk-hopping mechanism allows the SAA to have only a 2.5% relative CER degradation with a 320ms latency. After jointly training with a self-attention network language model, our SAA model obtains further error rate reduction on multiple datasets. Especially, it achieves 24.12% CER on the Mandarin ASR benchmark (HKUST), exceeding the best end-to-end model by over 2% absolute CER. |
| Self-Attention Based Sequential Model (SASRec) |
Sequential dynamics are a key feature of many modern recommender systems, which seek to capture the `context’ of users’ activities on the basis of actions they have performed recently. To capture such patterns, two approaches have proliferated: Markov Chains (MCs) and Recurrent Neural Networks (RNNs). Markov Chains assume that a user’s next action can be predicted on the basis of just their last (or last few) actions, while RNNs in principle allow for longer-term semantics to be uncovered. Generally speaking, MC-based methods perform best in extremely sparse datasets, where model parsimony is critical, while RNNs perform better in denser datasets where higher model complexity is affordable. The goal of our work is to balance these two goals, by proposing a self-attention based sequential model (SASRec) that allows us to capture long-term semantics (like an RNN), but, using an attention mechanism, makes its predictions based on relatively few actions (like an MC). At each time step, SASRec seeks to identify which items are `relevant’ from a user’s action history, and use them to predict the next item. Extensive empirical studies show that our method outperforms various state-of-the-art sequential models (including MC/CNN/RNN-based approaches) on both sparse and dense datasets. Moreover, the model is an order of magnitude more efficient than comparable CNN/RNN-based models. Visualizations on attention weights also show how our model adaptively handles datasets with various density, and uncovers meaningful patterns in activity sequences. |
| Self-Attention Capsule Network (SACN) |
We propose a novel architecture for image classification, called Self-Attention Capsule Networks (SACN). SACN is the first model that incorporates the Self-Attention mechanism as an integral layer within the Capsule Network (CapsNet). While the Self-Attention mechanism selects the more dominant image regions to focus on, the CapsNet analyzes the relevant features and their spatial correlations inside these regions only. The features are extracted in the convolutional layer. Then, the Self-Attention layer learns to suppress irrelevant regions based on features analysis, and highlights salient features useful for a specific task. The attention map is then fed into the CapsNet primary layer that is followed by a classification layer. The SACN proposed model was designed to use a relatively shallow CapsNet architecture to reduce computational load, and compensates for the absence of a deeper network by using the Self-Attention module to significantly improve the results. The proposed Self-Attention CapsNet architecture was extensively evaluated on five different datasets, mainly on three different medical sets, in addition to the natural MNIST and SVHN. The model was able to classify images and their patches with diverse and complex backgrounds better than the baseline CapsNet. As a result, the proposed Self-Attention CapsNet significantly improved classification performance within and across different datasets and outperformed the baseline CapsNet not only in classification accuracy but also in robustness. |
| Self-Attention Generative Adversarial Network (SAGAN) |
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points in lower-resolution feature maps. In SAGAN, details can be generated using cues from all feature locations. Moreover, the discriminator can check that highly detailed features in distant portions of the image are consistent with each other. Furthermore, recent work has shown that generator conditioning affects GAN performance. Leveraging this insight, we apply spectral normalization to the GAN generator and find that this improves training dynamics. The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset. Visualization of the attention layers shows that the generator leverages neighborhoods that correspond to object shapes rather than local regions of fixed shape. |
| Self-Attentive BiLSTM-CRF with Flair Embedding (SCIFI) |
Causality extraction from natural language texts is a challenging open problem in artificial intelligence. Existing methods utilize patterns, constraints, and machine learning techniques to extract causality, heavily depend on domain knowledge and require considerable human efforts and time on feature engineering. In this paper, we formulate causality extraction as a sequence tagging problem based on a novel causality tagging scheme. On this basis, we propose a neural causality extractor with BiLSTM-CRF model as the backbone, named SCIFI (Self-Attentive BiLSTM-CRF with Flair Embeddings), which can directly extract Cause and Effect, without extracting candidate causal pairs and identifying their relations separately. To tackle the problem of data insufficiency, we transfer the contextual string embeddings, also known as Flair embeddings, which trained on a large corpus into our task. Besides, to improve the performance of causality extraction, we introduce the multi-head self-attention mechanism into SCIFI to learn the dependencies between causal words. We evaluate our method on a public dataset, and experimental results demonstrate that our method achieves significant and consistent improvement as compared to other baselines. |
| Self-Attentive Neural Collaborative Filtering (SA-NCF) |
The dominant, state-of-the-art collaborative filtering (CF) methods today mainly comprises neural models. In these models, deep neural networks, e.g.., multi-layered perceptrons (MLP), are often used to model nonlinear relationships between user and item representations. As opposed to shallow models (e.g., factorization-based models), deep models generally provide a greater extent of expressiveness, albeit at the expense of impaired/restricted information flow. Consequently, the performance of most neural CF models plateaus at 3-4 layers, with performance stagnating or even degrading when increasing the model depth. As such, the question of how to train really deep networks in the context of CF remains unclear. To this end, this paper proposes a new technique that enables training neural CF models all the way up to 20 layers and beyond. Our proposed approach utilizes a new hierarchical self-attention mechanism that learns introspective intra-feature similarity across all the hidden layers of a standard MLP model. All in all, our proposed architecture, SA-NCF (Self-Attentive Neural Collaborative Filtering) is a densely connected self-matching model that can be trained up to 24 layers without plateau-ing, achieving wide performance margins against its competitors. On several popular benchmark datasets, our proposed architecture achieves up to an absolute improvement of 23%-58% and 1.3x to 2.8x fold improvement in terms of nDCG@10 and Hit Ratio (HR@10) scores over several strong neural CF baselines. |
| Self-Binarizing Network | We present a method to train self-binarizing neural networks, that is, networks that evolve their weights and activations during training to become binary. To obtain similar binary networks, existing methods rely on the sign activation function. This function, however, has no gradients for non-zero values, which makes standard backpropagation impossible. To circumvent the difficulty of training a network relying on the sign activation function, these methods alternate between floating-point and binary representations of the network during training, which is sub-optimal and inefficient. We approach the binarization task by training on a unique representation involving a smooth activation function, which is iteratively sharpened during training until it becomes a binary representation equivalent to the sign activation function. Additionally, we introduce a new technique to perform binary batch normalization that simplifies the conventional batch normalization by transforming it into a simple comparison operation. This is unlike existing methods, which are forced to the retain the conventional floating-point-based batch normalization. Our binary networks, apart from displaying advantages of lower memory and computation as compared to conventional floating-point and binary networks, also show higher classification accuracy than existing state-of-the-art methods on multiple benchmark datasets. |
| Self-Concordant Regularization in Bandit Learning (SCRiBLe) |
SCRiBLe (Self-Concordant Regularization in Bandit Learning) created by Abernethy et. al.\cite{abernethy}. The SCRiBLe setup and algorithm yield a $O(\sqrt{T})$ regret bound and polynomial run time complexity bound on the dimension of the input space. |
| Self-constructive Artificial Intelligence (SCAI) |
Towards Self-constructive Artificial Intelligence: Algorithmic basis (Part I) |
| Self-Controlled Case Series Model (SCCS) |
The self-controlled case series (SCCS) method is an alternative study method for investigating the association between a transient exposure and an adverse event. The method was developed to study adverse reactions to vaccines. The method uses only cases, no separate controls are required as the cases act as their own controls. Each case’s given observation time is divided into control and risk periods. Risk periods are defined during or after the exposure. Then the method finds a relative incidence, that is, the incidence in risk periods relative to the incidence in control periods. Time-varying confounding factors such as age can be allowed for by dividing up the observation period further into age categories. An advantage of the method is that confounding factors that do not vary with time, such as genetics, location, socio-economic status are controlled for implicitly. SCCS |
| Self-Critique and Adaptor (SCA) |
In few-shot learning, a machine learning system learns from a small set of labelled examples relating to a specific task, such that it can generalize to new examples of the same task. Given the limited availability of labelled examples in such tasks ,we wish to make use of all the information we can. Usually a model learns task-specific information from a small training-set (support-set) to predict on an unlabelled validation set (target-set). The target-set contains additional task-specific information which is not utilized by existing few-shot learning methods. Making use of the target-set examples via transductive learning requires approaches beyond the current methods; at inference time, the target-set contains only unlabelled input data-points, and so discriminative learning cannot be used. In this paper, we propose a framework called Self-Critique and Adaptor SCA, which learns to learn a label-free loss function, parameterized as a neural network. A base-model learns on a support-set using existing methods (e.g. stochastic gradient descent combined with the cross-entropy loss), and then is updated for the incoming target-task using the learnt loss function. This label-free loss function is itself optimized such that the learnt model achieves higher generalization performance. Experiments demonstrate that SCA offers substantially reduced error-rates compared to baselines which only adapt on the support-set, and results in state of the art benchmark performance on Mini-ImageNet and Caltech-UCSD Birds 200. |
| Self-Ensembling GCN (SEGCN) |
Graph convolutional network (GCN) provides a powerful means for graph-based semi-supervised tasks. However, as a localized first-order approximation of spectral graph convolution, the classic GCN can not take full advantage of unlabeled data, especially when the unlabeled node is far from labeled ones. To capitalize on the information from unlabeled nodes to boost the training for GCN, we propose a novel framework named Self-Ensembling GCN (SEGCN), which marries GCN with Mean Teacher – another powerful model in semi-supervised learning. SEGCN contains a student model and a teacher model. As a student, it not only learns to correctly classify the labeled nodes, but also tries to be consistent with the teacher on unlabeled nodes in more challenging situations, such as a high dropout rate and graph collapse. As a teacher, it averages the student model weights and generates more accurate predictions to lead the student. In such a mutual-promoting process, both labeled and unlabeled samples can be fully utilized for backpropagating effective gradients to train GCN. In three article classification tasks, i.e. Citeseer, Cora and Pubmed, we validate that the proposed method matches the state of the arts in the classification accuracy. |
| Self-Exciting Model of Information Cascades (SEISMIC) |
Here we focus on predicting the final size of an information cascade spreading through a network. We develop a statistical model based on the theory of self-exciting point processes. A point process indexed by time is called a counting process when it counts the number of instances (reshares, in our case) over time. In contrast to homogeneous Poisson processes which assume constant intensity over time, self-exciting processes assume that all the previous instances (i.e., reshares) influence the future evolution of the process. Self-exciting point processes are frequently used to model ‘rich get richer’ phenomena. They are ideal for modeling information cascades in networks because every new reshare of a post not only increases its cumulative reshare count by one, but also exposes new followers who may further reshare the post. We develop SEISMIC (Self-Exciting Model of Information Cascades) for predicting the total number of reshares of a given post. In our model, each post is fully characterized by its infectiousness which measures the reshare probability. We allow the infectiousness to vary freely over time in agreement with the observation that the infectiousness can drop as the content gets stale. Moreover, our model is able to identify at each time point whether the cascade is in the supercritical or subcritical state, based on whether its infectiousness is above or below a critical threshold. A cascade in the supercritical state is going through an ‘explosion’ period and its final size cannot be predicted accurately at the current time. On the contrary, a cascade is tractable if it is in subcritical state. In this case, we are able to predict its ultimate popularity accurately by modeling the future cascading behavior by a Galton- Watson tree. Our SEISMIC approach makes several contributions: Generative model: SEISMIC imposes no parametric assumptions and requires no expensive feature engineering. Moreover, as complete social network structure may be hard to obtain, SEISMIC assumes minimal knowledge of the network: The only required input is the time history of reshares and the degrees of the resharing nodes. seismic |
| Self-Exciting Point Process Model | seismic |
| Self-Guided Belief Propagation (SBP) |
We propose self-guided belief propagation (SBP) that modifies belief propagation (BP) by incorporating the pairwise potentials only gradually. This homotopy continuation method converges to a unique solution and increases the accuracy without increasing the computational burden. We apply SBP to grid graphs, complete graphs, and random graphs with random Ising potentials and show that: (i) SBP is superior in terms of accuracy whenever BP converges, and (ii) SBP obtains a unique, stable, and accurate solution whenever BP does not converge. We further provide a formal analysis to demonstrate that SBP obtains the global optimum of the Bethe approximation for attractive models with unidirectional fields. |
| Self-Imitation Learning (SIL) |
This paper proposes Self-Imitation Learning (SIL), a simple off-policy actor-critic algorithm that learns to reproduce the agent’s past good decisions. This algorithm is designed to verify our hypothesis that exploiting past good experiences can indirectly drive deep exploration. Our empirical results show that SIL significantly improves advantage actor-critic (A2C) on several hard exploration Atari games and is competitive to the state-of-the-art count-based exploration methods. We also show that SIL improves proximal policy optimization (PPO) on MuJoCo tasks. |
| Selfless Sequential Learning | Sequential learning studies the problem of learning tasks in a sequence with restricted access to only the data of the current task. In the setting with a fixed model capacity, the learning process should not be selfish and account for later tasks to be added and therefore aim at utilizing a minimum number of neurons, leaving enough capacity for future needs. We explore different regularization strategies and activation functions that could lead to less interference between the different tasks. We show that learning a sparse representation is more beneficial for sequential learning than encouraging parameter sparsity regardless of their corresponding neurons. We particularly propose a novel regularizer that encourages representation sparsity by means of neural inhibition. It results in few active neurons which in turn leaves more free neurons to be utilized by upcoming tasks. We combine our regularizer with state-of-the-art lifelong learning methods that penalize changes on important previously learned parts of the network. We show that increased sparsity translates in a performance improvement on the different tasks that are learned in a sequence. |
| Self-Normalizing Neural Network | Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNNs) are rare. FNNs that perform well are typically shallow and, therefore cannot exploit many levels of abstract representations. We introduce self-normalizing neural networks (SNNs) to enable high-level abstract representations. While batch normalization requires explicit normalization, neuron activations of SNNs automatically converge towards zero mean and unit variance. The activation function of SNNs are ‘scaled exponential linear units’ (SELUs), which induce self-normalizing properties. Using the Banach fixed-point theorem, we prove that activations close to zero mean and unit variance that are propagated through many network layers will converge towards zero mean and unit variance — even under the presence of noise and perturbations. This convergence property of SNNs allows to (1) train deep networks with many layers, (2) employ strong regularization, and (3) to make learning highly robust. Furthermore, for activations not close to unit variance, we prove an upper and lower bound on the variance, thus, vanishing and exploding gradients are impossible. We compared SNNs on (a) 121 tasks from the UCI machine learning repository, on (b) drug discovery benchmarks, and on (c) astronomy tasks with standard FNNs and other machine learning methods such as random forests and support vector machines. SNNs significantly outperformed all competing FNN methods at 121 UCI tasks, outperformed all competing methods at the Tox21 dataset, and set a new record at an astronomy data set. The winning SNN architectures are often very deep. Implementations are available at: github.com/bioinf-jku/SNNs. |
| Self-Organising Eigenspace Map (SOEM) |
This paper presents a novel time series clustering method, the self-organising eigenspace map (SOEM), based on a generalisation of the well-known self-organising feature map (SOFM). The SOEM operates on the eigenspaces of the embedded covariance structures of time series which are related directly to modes in those time series. Approximate joint diagonalisation acts as a pseudo-metric across these spaces allowing us to generalise the SOFM to a neural network with matrix input. The technique is empirically validated against three sets of experiments; univariate and multivariate time series clustering, and application to (clustered) multi-variate time series forecasting. Results indicate that the technique performs a valid topologically ordered clustering of the time series. The clustering is superior in comparison to standard benchmarks when the data is non-aligned, gives the best clustering stage for when used in forecasting, and can be used with partial/non-overlapping time series, multivariate clustering and produces a topological representation of the time series objects. |
| Self-Organizing Map (SOM) |
A self-organizing map (SOM) or self-organizing feature map (SOFM) is a type of artificial neural network (ANN) that is trained using unsupervised learning to produce a low-dimensional (typically two-dimensional), discretized representation of the input space of the training samples, called a map. Self-organizing maps are different from other artificial neural networks in the sense that they use a neighborhood function to preserve the topological properties of the input space. This makes SOMs useful for visualizing low-dimensional views of high-dimensional data, akin to multidimensional scaling. The model was first described as an artificial neural network by the Finnish professor Teuvo Kohonen, and is sometimes called a Kohonen map or network. |
| Self-Organizing Systems | The term Self-organizing Systems refers to a class of systems that are able to change their internal structure and their function in response to external circumstances. By self-organization it is understood that elements of a system are able to manipulate or organize other elements of the same system in a way that stabilizes either structure or function of the whole against external fluctuations. Over the last decades a variety of features have been identified as typical for self-organizing systems. Not all of these features are present in all systems able to self-organize. Self-organizing systems are dynamic, non-deterministic, open, exist far from equilibrium and sometimes employ autocatalytic amplification of fluctuations. Often, they are characterized by multiple time-scales of their internal and/or external interactions, they possess a hierarchy of structural and/or functional levels and they are able to react to external input in a variety of ways. Many self-organizing systems are non-teleological, i.e. they do not have a specific purpose except their own existence. As a consequence, self-maintenance is an important function of many self-organizing systems. Most of these systems are complex and use reduncancy to achieve resilience against external pertubation tendencies. Self-organizing systems have been discovered in nature, both in the non-living (galaxies, stars) and the living world (cells, organisms, ecosystems), they have been found in man-made systems (societies, economies), and they have been identified in the world of ideas (world views, scientific believes, norm systems). Self Organizing System |
| Self-Paced Learning (SPL) |
It is known that Boosting can be interpreted as a gradient descent technique to minimize an underlying loss function. Specifically, the underlying loss being minimized by the traditional AdaBoost is the exponential loss, which is proved to be very sensitive to random noise/outliers. Therefore, several Boosting algorithms, e.g., LogitBoost and SavageBoost, have been proposed to improve the robustness of AdaBoost by replacing the exponential loss with some designed robust loss functions. In this work, we present a new way to robustify AdaBoost, i.e., incorporating the robust learning idea of Self-paced Learning (SPL) into Boosting framework. Specifically, we design a new robust Boosting algorithm based on SPL regime, i.e., SPLBoost, which can be easily implemented by slightly modifying off-the-shelf Boosting packages. Extensive experiments and a theoretical characterization are also carried out to illustrate the merits of the proposed SPLBoost. |
| Self-Paced Multi-Task Clustering (SPMTC) |
Multi-task clustering (MTC) has attracted a lot of research attentions in machine learning due to its ability in utilizing the relationship among different tasks. Despite the success of traditional MTC models, they are either easy to stuck into local optima, or sensitive to outliers and noisy data. To alleviate these problems, we propose a novel self-paced multi-task clustering (SPMTC) paradigm. In detail, SPMTC progressively selects data examples to train a series of MTC models with increasing complexity, thus highly decreases the risk of trapping into poor local optima. Furthermore, to reduce the negative influence of outliers and noisy data, we design a soft version of SPMTC to further improve the clustering performance. The corresponding SPMTC framework can be easily solved by an alternating optimization method. The proposed model is guaranteed to converge and experiments on real data sets have demonstrated its promising results compared with state-of-the-art multi-task clustering methods. |
| Self-Paced Probabilistic Principal Component Analysis (SP-PPCA) |
Principal Component Analysis (PCA) is a popular tool for dimensionality reduction and feature extraction in data analysis. There is a probabilistic version of PCA, known as Probabilistic PCA (PPCA). However, standard PCA and PPCA are not robust, as they are sensitive to outliers. To alleviate this problem, this paper introduces the Self-Paced Learning mechanism into PPCA, and proposes a novel method called Self-Paced Probabilistic Principal Component Analysis (SP-PPCA). Furthermore, we design the corresponding optimization algorithm based on the alternative search strategy and the expectation-maximization algorithm. SP-PPCA looks for optimal projection vectors and filters out outliers iteratively. Experiments on both synthetic problems and real-world datasets clearly demonstrate that SP-PPCA is able to reduce or eliminate the impact of outliers. |
| Self-Paced Sparse Coding (SPSC) |
Sparse coding (SC) is attracting more and more attention due to its comprehensive theoretical studies and its excellent performance in many signal processing applications. However, most existing sparse coding algorithms are nonconvex and are thus prone to becoming stuck into bad local minima, especially when there are outliers and noisy data. To enhance the learning robustness, in this paper, we propose a unified framework named Self-Paced Sparse Coding (SPSC), which gradually include matrix elements into SC learning from easy to complex. We also generalize the self-paced learning schema into different levels of dynamic selection on samples, features and elements respectively. Experimental results on real-world data demonstrate the efficacy of the proposed algorithms. |
| Self-Reducibility | This chapter provides a hands-on tutorial on the important technique known as self-reducibility. Through a series of ‘Challenge Problems’ that are theorems that the reader will—after being given definitions and tools—try to prove, the tutorial will ask the reader not to read proofs that use self-reducibility, but rather to discover proofs that use self-reducibility. In particular, the chapter will seek to guide the reader to the discovery of proofs of four interesting theorems—whose focus areas range from selectivity to information to approximation—from the literature, whose proofs draw on self-reducibility. The chapter’s goal is to allow interested readers to add self-reducibility to their collection of proof tools. The chapter simultaneously has a related but different goal, namely, to provide a ‘lesson plan’ (and a coordinated set of slides is available online to support this use [Hem19]) for a lecture to a two-lecture series that can be given to undergraduate students—even those with no background other than basic discrete mathematics and an understanding of what polynomial-time computation is—to immerse them in hands-on proving, and by doing that, to serve as an invitation to them to take courses on Models of Computation or Complexity Theory. |
| Self-Referenced Deep Learning (SRDL) |
Knowledge distillation is an effective approach to transferring knowledge from a teacher neural network to a student target network for satisfying the low-memory and fast running requirements in practice use. Whilst being able to create stronger target networks compared to the vanilla non-teacher based learning strategy, this scheme needs to train additionally a large teacher model with expensive computational cost. In this work, we present a Self-Referenced Deep Learning (SRDL) strategy. Unlike both vanilla optimisation and existing knowledge distillation, SRDL distils the knowledge discovered by the in-training target model back to itself to regularise the subsequent learning procedure therefore eliminating the need for training a large teacher model. SRDL improves the model generalisation performance compared to vanilla learning and conventional knowledge distillation approaches with negligible extra computational cost. Extensive evaluations show that a variety of deep networks benefit from SRDL resulting in enhanced deployment performance on both coarse-grained object categorisation tasks (CIFAR10, CIFAR100, Tiny ImageNet, and ImageNet) and fine-grained person instance identification tasks (Market-1501). |
| Self-Service Semantic Suite (S4) |
The Self-Service Semantic Suite (S4) provides a set of services for low-cost, on-demand text analytics and metadata management on the cloud. S4 provides the following services: · Text analytics services for news, Life Science and social media that allow you to extract valuable meaning and insights used to manage your business · On-demand, fast and reliable access to Linked Datasets, such as DBpedia, Freebase and GeoNames. These datasets provide facts you can use to enhance your semantic analysis. · A self-managed or fully-managed scalable RDF database available as-a-service, so that you can search and update semantic facts loaded from Linked Open Data or your own documents |
| Self-Supervised Convolutional Subspace Clustering Network (S^2ConvSCN) |
Subspace clustering methods based on data self-expression have become very popular for learning from data that lie in a union of low-dimensional linear subspaces. However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces. On the other hand, while Convolutional Neural Network (ConvNet) has been demonstrated to be a powerful tool for extracting discriminative features from visual data, training such a ConvNet usually requires a large amount of labeled data, which are unavailable in subspace clustering applications. To achieve simultaneous feature learning and subspace clustering, we propose an end-to-end trainable framework, called Self-Supervised Convolutional Subspace Clustering Network (S$^2$ConvSCN), that combines a ConvNet module (for feature learning), a self-expression module (for subspace clustering) and a spectral clustering module (for self-supervision) into a joint optimization framework. Particularly, we introduce a dual self-supervision that exploits the output of spectral clustering to supervise the training of the feature learning module (via a classification loss) and the self-expression module (via a spectral clustering loss). Our experiments on four benchmark datasets show the effectiveness of the dual self-supervision and demonstrate superior performance of our proposed approach. |
| Self-Supervised Semi-Supervised Learning (S^4L) |
This work tackles the problem of semi-supervised learning of image classifiers. Our main insight is that the field of semi-supervised learning can benefit from the quickly advancing field of self-supervised visual representation learning. Unifying these two approaches, we propose the framework of self-supervised semi-supervised learning ($S^4L$) and use it to derive two novel semi-supervised image classification methods. We demonstrate the effectiveness of these methods in comparison to both carefully tuned baselines, and existing semi-supervised learning methods. We then show that $S^4L$ and existing semi-supervised methods can be jointly trained, yielding a new state-of-the-art result on semi-supervised ILSVRC-2012 with 10% of labels. |
| Self-Supervised Spectral Graph Representation Learning (SGR) |
Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and analytical task at hand. Unfortunately, a ‘one-size-fits-all’ solution is unattainable, as different analytical tasks may require different attention to global or local graph features. We develop SGR, the first, to our knowledge, method for learning graph representations in a self-supervised manner. Grounded on spectral graph analysis, SGR seamlessly combines all aforementioned desirable properties. In extensive experiments, we show how our approach works on large graph collections, facilitates self-supervised representation learning across a variety of application domains, and performs competitively to state-of-the-art methods without re-training. |
| Self-Taught Associative Memory (STAM) |
We first pose the Unsupervised Continual Learning (UCL) problem: learning salient representations from a non-stationary stream of unlabeled data in which the number of object classes varies with time. Given limited labeled data just before inference, those representations can also be associated with specific object types to perform classification. To solve the UCL problem, we propose an architecture that involves a single module, called Self-Taught Associative Memory (STAM), which loosely models the function of a cortical column in the mammalian brain. Hierarchies of STAM modules learn based on a combination of Hebbian learning, online clustering, detection of novel patterns, forgetting outliers, and top-down predictions. We illustrate the operation of STAMs in the context of learning handwritten digits in a continual manner with only 3-12 labeled examples per class. STAMs suggest a promising direction to solve the UCL problem without catastrophic forgetting. |
| Self-Taught Learning | Self-taught learning is a new paradigm in machine learning introduced by Stanford researchers in 2007. ‘Self-taught Learning: Transfer Learning from Unlabeled Data’. Proceedings of the 24th International Conference on Machine Learning, Corvallis, OR.</ref>. The full paper can be found here. It builds on ideas from existing supervised, semi-supervised and transfer learning algorithms. The differences between these methods depend on the usage of labeled and unlabeled data (Figure 1): • Supervised Learning – All data is labeled and of the same type (shares the same class labels). • Semi-supervised learning – Only some of the data is labeled but it is all of the same class. One drawback is that acquiring unlabeled data of the same class is often difficult and/or expensive. • Transfer learning – All data is labeled but some is of another type (i.e. has class labels that do not apply to data set that we wish to classify). Self-taught learning combines the latter two ideas. It uses labeled data belonging to the desired classes and unlabeled data from other, somehow similar, classes. It is important to emphasize that the unlabeled data need not belong to the class labels we wish to assign, as long as it is related. This fact distinguishes it from semi-supervised learning. Since it uses unlabeled data from new classes, it can be thought of as semi-supervised transfer learning. Self-taught learning is a technique that uses a large number of unlabeled data as source samples to improve the task performance on target samples. Compared with other transfer learning techniques, self-taught learning can be applied to a broader set of scenarios due to the loose restrictions on source data. However, knowledge transferred from source samples that are not sufficiently related to the target domain may negatively influence the target learner, which is referred to as negative transfer. Autoencoder Based Sample Selection for Self-Taught Learning |
| Self-Taught Support Vector Machine | In this paper, a new approach for classification of target task using limited labeled target data as well as enormous unlabeled source data is proposed which is called self-taught learning. The target and source data can be drawn from different distributions. In the previous approaches, covariate shift assumption is considered where the marginal distributions p(x) change over domains and the conditional distributions p(y|x) remain the same. In our approach, we propose a new objective function which simultaneously learns a common space T(.) where the conditional distributions over domains p(T(x)|y) remain the same and learns robust SVM classifiers for target task using both source and target data in the new representation. Hence, in the proposed objective function, the hidden label of the source data is also incorporated. We applied the proposed approach on Caltech-256, MSRC+LMO datasets and compared the performance of our algorithm to the available competing methods. Our method has a superior performance to the successful existing algorithms. |
| Self-weighted Multiview Metric Learning (SM2L) |
With the development of multimedia time, one sample can always be described from multiple views which contain compatible and complementary information. Most algorithms cannot take information from multiple views into considerations and fail to achieve desirable performance in most situations. For many applications, such as image retrieval, face recognition, etc., an appropriate distance metric can better reflect the similarities between various samples. Therefore, how to construct a good distance metric learning methods which can deal with multiview data has been an important topic during the last decade. In this paper, we proposed a novel algorithm named Self-weighted Multiview Metric Learning (SM2L) which can finish this task by maximizing the cross correlations between different views. Furthermore, because multiple views have different contributions to the learning procedure of SM2L, we adopt a self-weighted learning framework to assign multiple views with different weights. Various experiments on benchmark datasets can verify the performance of our proposed method. |
| Semantic Adversarial Deep Learning | Fueled by massive amounts of data, models produced by machine-learning (ML) algorithms, especially deep neural networks, are being used in diverse domains where trustworthiness is a concern, including automotive systems, finance, health care, natural language processing, and malware detection. Of particular concern is the use of ML algorithms in cyber-physical systems (CPS), such as self-driving cars and aviation, where an adversary can cause serious consequences. However, existing approaches to generating adversarial examples and devising robust ML algorithms mostly ignore the semantics and context of the overall system containing the ML component. For example, in an autonomous vehicle using deep learning for perception, not every adversarial example for the neural network might lead to a harmful consequence. Moreover, one may want to prioritize the search for adversarial examples towards those that significantly modify the desired semantics of the overall system. Along the same lines, existing algorithms for constructing robust ML algorithms ignore the specification of the overall system. In this paper, we argue that the semantics and specification of the overall system has a crucial role to play in this line of research. We present preliminary research results that support this claim. |
| Semantic Adversarial Diagnostic Attack (SADA) |
One major factor impeding more widespread adoption of deep neural networks (DNNs) is their issues with robustness, which is essential for safety critical applications such as autonomous driving. This has motivated much recent work on adversarial attacks for DNNs, which mostly focus on pixel-level perturbations void of semantic meaning. In contrast, we present a general framework for adversarial black box attacks on agents, which are intimately related to the semantics of the task being performed by the agent. To do this, our proposed adversary (denoted as BBGAN) is trained to appropriately parametrize the environment (black box) with which the agent interacts, such that this agent performs poorly on its dedicated task. We illustrate the application of our BBGAN framework on three different tasks (primarily targeting aspects of autonomous navigation): object detection, self-driving, and autonomous UAV racing. On these tasks, our approach can be used to generate failure cases that fool an agent consistently. |
| Semantic Analysis | Semantic analysis may refer to: · Semantic analysis (compilers) · Semantic analysis (machine learning) · Semantic analysis (knowledge representation) · Semantic analysis (linguistics) |
| Semantic Analysis Approach for Recommendation (SAR) |
Recommendation system is a common demand in daily life and matrix completion is a widely adopted technique for this task. However, most matrix completion methods lack semantic interpretation and usually result in weak-semantic recommendations. To this end, this paper proposes a {\bf S}emantic {\bf A}nalysis approach for {\bf R}ecommendation systems \textbf{(SAR)}, which applies a two-level hierarchical generative process that assigns semantic properties and categories for user and item. SAR learns semantic representations of users/items merely from user ratings on items, which offers a new path to recommendation by semantic matching with the learned representations. Extensive experiments demonstrate SAR outperforms other state-of-the-art baselines substantially. |
| Semantic Analytics | Semantic analytics is the use of ontologies to analyze content in web resources. This field of research combines text analytics and Semantic Web technologies like RDF. |
| Semantic Analytics Visualization (SAV) |
In this paper we present a new tool for semantic analytics through 3D visualization called ‘Semantic Analytics Visualization’ (SAV). It has the capability for visualizing ontologies and meta-data including annotated webdocuments, images, and digital media such as audio and video clips in a synthetic three-dimensional semi-immersive environment. More importantly, SAV supports visual semantic analytics, whereby an analyst can interactively investigate complex relationships between heterogeneous information. The tool is built using Virtual Reality technology which makes SAV a highly interactive system. The backend of SAV consists of a Semantic Analytics system that supports query processing and semantic association discovery. Using a virtual laser pointer, the user can select nodes in the scene and either play digital media, display images, or load annotated web documents. SAV can also display the ranking of web documents as well as the ranking of paths (sequences of links). SAV supports dynamic specification of sub-queries of a given graph and displays the results based on ranking information, which enables the users to find, analyze and comprehend the information presented quickly and accurately. |
| Semantic Anticipation | Recurrent Flow-Guided Semantic Forecasting |
| Semantic Attribute Matching Network (SAM-Net) |
We present semantic attribute matching networks (SAM-Net) for jointly establishing correspondences and transferring attributes across semantically similar images, which intelligently weaves the advantages of the two tasks while overcoming their limitations. SAM-Net accomplishes this through an iterative process of establishing reliable correspondences by reducing the attribute discrepancy between the images and synthesizing attribute transferred images using the learned correspondences. To learn the networks using weak supervisions in the form of image pairs, we present a semantic attribute matching loss based on the matching similarity between an attribute transferred source feature and a warped target feature. With SAM-Net, the state-of-the-art performance is attained on several benchmarks for semantic matching and attribute transfer. |
| Semantic Brand Score (SBS) |
The Semantic Brand Score (SBS) is a new measure of brand importance calculated on text data, combining methods of social network and semantic analysis. This metric is flexible as it can be used in different contexts and across products, markets and languages. It is applicable not only to brands, but also to multiple sets of words. The SBS, described together with its three dimensions of brand prevalence, diversity and connectivity, represents a contribution to the research on brand equity and on word co-occurrence networks. It can be used to support decision-making processes within companies; for example, it can be applied to forecast a company’s stock price or to assess brand importance with respect to competitors. On the one side, the SBS relates to familiar constructs of brand equity, on the other, it offers new perspectives for effective strategic management of brands in the era of big data. |
| Semantic Correspondences Convolutional Neural Network (SCNet) |
This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category. Previous approaches focus on either combining a spatial regularizer with hand-crafted features, or learning a correspondence model for appearance only. We propose instead a convolutional neural network architecture, called SCNet, for learning a geometrically plausible model for semantic correspondence. SCNet uses region proposals as matching primitives, and explicitly incorporates geometric consistency in its loss function. It is trained on image pairs obtained from the PASCAL VOC 2007 keypoint dataset, and a comparative evaluation on several standard benchmarks demonstrates that the proposed approach substantially outperforms both recent deep learning architectures and previous methods based on hand-crafted features. |
| Semantic Differential | Semantic differential is a type of a rating scale designed to measure the connotative meaning of objects, events, and concepts. The connotations are used to derive the attitude towards the given object, event or concept. Osgood’s semantic differential was an application of his more general attempt to measure the semantics or meaning of words, particularly adjectives, and their referent concepts. The respondent is asked to choose where his or her position lies, on a scale between two bipolar adjectives (for example: “Adequate-Inadequate”, “Good-Evil” or “Valuable-Worthless”). Semantic differentials can be used to measure opinions, attitudes and values on a psychometrically controlled scale. |
| Semantic Edge-Aware Strategy (SEMEDA) |
While nowadays deep neural networks achieve impressive performances on semantic segmentation tasks, they are usually trained by optimizing pixel-wise losses such as cross-entropy. As a result, the predictions outputted by such networks usually struggle to accurately capture the object boundaries and exhibit holes inside the objects. In this paper, we propose a novel approach to improve the structure of the predicted segmentation masks. We introduce a novel semantic edge detection network, which allows to match the predicted and ground truth segmentation masks. This Semantic Edge-Aware strategy (SEMEDA) can be combined with any backbone deep network in an end-to-end training framework. Through thorough experimental validation on Pascal VOC 2012 and Cityscapes datasets, we show that the proposed SEMEDA approach enhances the structure of the predicted segmentation masks by enforcing sharp boundaries and avoiding discontinuities inside objects, improving the segmentation performance. In addition, our semantic edge-aware loss can be integrated into any popular segmentation network without requiring any additional annotation and with negligible computational load, as compared to standard pixel-wise cross-entropy loss. |
| Semantic Entity Retrieval Toolkit (SERT) |
Unsupervised learning of low-dimensional, semantic representations of words and entities has recently gained attention. In this paper we describe the Semantic Entity Retrieval Toolkit (SERT) that provides implementations of our previously published entity representation models. The toolkit provides a unified interface to different representation learning algorithms, fine-grained parsing configuration and can be used transparently with GPUs. In addition, users can easily modify existing models or implement their own models in the framework. After model training, SERT can be used to rank entities according to a textual query and extract the learned entity/word representation for use in downstream algorithms, such as clustering or recommendation. |
| Semantic Entropy (E) |
A time series is uniquely represented by its geometric shape, which also carries information. A time series can be modelled as the trajectory of a particle moving in a force field with one degree of freedom. The force acting on the particle shapes the trajectory of its motion, which is made up of elementary shapes of infinitesimal neighborhoods of points in the trajectory. It has been proved that an infinitesimal neighborhood of a point in a continuous time series can have at least 29 different shapes or configurations. So information can be encoded in it in at least 29 different ways. A 3-point neighborhood (the smallest) in a discrete time series can have precisely 13 different shapes or configurations. In other words, a discrete time series can be expressed as a string of 13 symbols. Across diverse real as well as simulated data sets it has been observed that 6 of them occur more frequently and the remaining 7 occur less frequently. Based on frequency distribution of 13 configurations or 13 different ways of information encoding a novel entropy measure, called semantic entropy (E), has been defined. Following notion of power in Newtonian mechanics of the moving particle whose trajectory is the time series, a notion of information power (P) has been introduced for time series. E/P turned out to be an important indicator of synchronous behaviour of time series as observed in epileptic EEG signals. |
| Semantic Evaluation (SemEval) |
SemEval (Semantic Evaluation) is an ongoing series of evaluations of computational semantic analysis systems; it evolved from the Senseval word sense evaluation series. The evaluations are intended to explore the nature of meaning in language. While meaning is intuitive to humans, transferring those intuitions to computational analysis has proved elusive. This series of evaluations is providing a mechanism to characterize in more precise terms exactly what is necessary to compute in meaning. As such, the evaluations provide an emergent mechanism to identify the problems and solutions for computations with meaning. These exercises have evolved to articulate more of the dimensions that are involved in our use of language. They began with apparently simple attempts to identify word senses computationally. They have evolved to investigate the interrelationships among the elements in a sentence (e.g., semantic role labeling), relations between sentences (e.g., coreference), and the nature of what we are saying (semantic relations and sentiment analysis). The purpose of the SemEval exercises and SENSEVAL is to evaluate semantic analysis systems. ‘Semantic Analysis’ refers to a formal analysis of meaning, and ‘computational’ refer to approaches that in principle support effective implementation. The first three evaluations, Senseval-1 through Senseval-3, were focused on word sense disambiguation, each time growing in the number of languages offered in the tasks and in the number of participating teams. Beginning with the fourth workshop, SemEval-2007 (SemEval-1), the nature of the tasks evolved to include semantic analysis tasks outside of word sense disambiguation. Triggered by the conception of the *SEM conference, the SemEval community had decided to hold the evaluation workshops yearly in association with the *SEM conference. It was also the decision that not every evaluation task will be run every year, e.g. none of the WSD tasks were running in the SemEval-2012 workshop. |
| Semantic Feature Engine | We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label. We use a deep lattice network model so we can architect the model structure to enhance interpretability, and add monotonicity constraints between inputs-and-outputs. We then use the proposed set function to automate the engineering of dense, interpretable features from sparse categorical features, which we call semantic feature engine. Experiments on real-world data show the achieved accuracy is similar to deep sets or deep neural networks, and is easier to debug and understand. |
| Semantic Integration | Semantic integration is the process of interrelating information from diverse sources, for example calendars and to do lists, email archives, presence information (physical, psychological, and social), documents of all sorts, contacts (including social graphs), search results, and advertising and marketing relevance derived from them. In this regard, semantics focuses on the organization of and action upon information by acting as an intermediary between heterogeneous data sources, which may conflict not only by structure but also context or value. |
| Semantic Label Indexing, Neural Matching, and Efficient Ranking (SLINMER) |
Extreme multi-label classification (XMC) aims to assign to an instance the most relevant subset of labels from a colossal label set. Due to modern applications that lead to massive label sets, the scalability of XMC has attracted much recent attention from both academia and industry. In this paper, we establish a three-stage framework to solve XMC efficiently, which includes 1) indexing the labels, 2) matching the instance to the relevant indices, and 3) ranking the labels from the relevant indices. This framework unifies many existing XMC approaches. Based on this framework, we propose a modular deep learning approach SLINMER: Semantic Label Indexing, Neural Matching, and Efficient Ranking. The label indexing stage of SLINMER can adopt different semantic label representations leading to different configurations of SLINMER. Empirically, we demonstrate that several individual configurations of SLINMER achieve superior performance than the state-of-the-art XMC approaches on several benchmark datasets. Moreover, by ensembling those configurations, SLINMER can achieve even better results. In particular, on a Wiki dataset with around 0.5 millions of labels, the precision@1 is increased from 61% to 67%. |
| Semantic Labeling | Semantic labeling is the process of mapping attributes in data sources to classes in an ontology and is a necessary step in heterogeneous data integration. |
| Semantic Layer | A semantic layer is a business representation of corporate data that helps end users access data autonomously using common business terms. Developed and patented by Business Objects, it maps complex data into familiar business terms such as product, customer, or revenue to offer a unified, consolidated view of data across the organization. By using common business terms, rather than data language, to access, manipulate, and organize information, it simplifies the complexity of business data. These business terms are stored as objects in a universe, accessed through business views. Universes enable business users to access and analyze data stored in a relational database and OLAP cubes. This is claimed to be core business intelligence (BI) technology that frees users from IT while ensuring correct results. Business Views is a multi-tier system that is designed to enable companies to build comprehensive and specific business objects that help report designers and end users access the information they require. Business Views is intended to enable people to add the necessary business context to their data islands and link them into a single organized Business View for their organization. Semantic layer maps tables to classes and columns to objects. |
| Semantic Learning Machine (SLM) |
In iterative supervised learning algorithms it is common to reach a point in the search where no further induction seems to be possible with the available data. If the search is continued beyond this point, the risk of overfitting increases significantly. Following the recent developments in inductive semantic stochastic methods, this paper studies the feasibility of using information gathered from the semantic neighborhood to decide when to stop the search. Two semantic stopping criteria are proposed and experimentally assessed in Geometric Semantic Genetic Programming (GSGP) and in the Semantic Learning Machine (SLM) algorithm (the equivalent algorithm for neural networks). The experiments are performed on real-world high-dimensional regression datasets. The results show that the proposed semantic stopping criteria are able to detect stopping points that result in a competitive generalization for both GSGP and SLM. This approach also yields computationally efficient algorithms as it allows the evolution of neural networks in less than 3 seconds on average, and of GP trees in at most 10 seconds. The usage of the proposed semantic stopping criteria in conjunction with the computation of optimal mutation/learning steps also results in small trees and neural networks. |
| Semantic Lexicon | A semantic lexicon is a dictionary of words labeled with semantic classes so associations can be drawn between words that have not previously been encountered: it is a dictionary with a semantic network. |
| Semantic Matching | Semantic matching is a technique used in computer science to identify information which is semantically related. Given any two graph-like structures, e.g. classifications, taxonomies database or XML schemas and ontologies, matching is an operator which identifies those nodes in the two structures which semantically correspond to one another. For example, applied to file systems it can identify that a folder labeled ‘car’ is semantically equivalent to another folder ‘automobile’ because they are synonyms in English. This information can be taken from a linguistic resource like WordNet. In the recent years many of them have been offered. S-Match is an example of a semantic matching operator. It works on lightweight ontologies, namely graph structures where each node is labeled by a natural language sentence, for example in English. These sentences are translated into a formal logical formula (according to an artificial unambiguous language) codifying the meaning of the node taking into account its position in the graph. For example, in case the folder ‘car’ is under another folder ‘red’ we can say that the meaning of the folder ‘car’ is ‘red car’ in this case. This is translated into the logical formula ‘red AND car’. The output of S-Match is a set of semantic correspondences called mappings attached with one of the following semantic relations: disjointness (⊥), equivalence (≡), more specific (⊑) and less specific (⊒). In our example the algorithm will return a mapping between ‘car’ and ‘automobile’ attached with an equivalence relation. Information semantically matched can also be used as a measure of relevance through a mapping of near-term relationships. Such use of S-Match technology is prevalent in the career space where it is used to gauge depth of skills through relational mapping of information found in applicant resumes. Semantic matching represents a fundamental technique in many applications in areas such as resource discovery, data integration, data migration, query translation, peer to peer networks, agent communication, schema and ontology merging. It using is also being investigated in other areas such as event processing. In fact, it has been proposed as a valid solution to the semantic heterogeneity problem, namely managing the diversity in knowledge. Interoperability among people of different cultures and languages, having different viewpoints and using different terminology has always been a huge problem. Especially with the advent of the Web and the consequential information explosion, the problem seems to be emphasized. People face the concrete problem to retrieve, disambiguate and integrate information coming from a wide variety of sources. Semantic Matching Against a Corpus: New Applications and Methods |
| Semantic Memory | Semantic memory refers to a portion of long-term memory that processes ideas and concepts that are not drawn from personal experience. Semantic memory includes things that are common knowledge, such as the names of colors, the sounds of letters, the capitals of countries and other basic facts acquired over a lifetime. The concept of semantic memory is fairly new. It was introduced in 1972 as the result of collaboration between Endel Tulving of the University of Toronto and Wayne Donaldson of the University of New Brunswick on the impact of organization in human memory. Tulving outlined the separate systems of conceptualization of episodic and semantic memory in his book, ‘Elements of Episodic Memory.’ He noted that semantic and episodic differ in how they operate and the types of information they process. |
| Semantic Network | A semantic network, or frame network is a knowledge base that represents semantic relations between concepts in a network. This is often used as a form of knowledge representation. It is a directed or undirected graph consisting of vertices, which represent concepts, and edges, which represent semantic relations between concepts, mapping or connecting semantic fields. Typical standardized semantic networks are expressed as semantic triples. Semantic networks are in use in various Natural Language Processing applications. A Knowledge Grapg is a Semantic Network. |
| Semantic Parsing | Semantic parsing can be defined as the process of mapping natural language sentences into a machine interpretable, formal representation of its meaning. |
| Semantic Pixel-Level Adaptation Transform (SPLAT) |
Domain adaptation of visual detectors is a critical challenge, yet existing methods have overlooked pixel appearance transformations, focusing instead on bootstrapping and/or domain confusion losses. We propose a Semantic Pixel-Level Adaptation Transform (SPLAT) approach to detector adaptation that efficiently generates cross-domain image pairs. Our model uses aligned-pair and/or pseudo-label losses to adapt an object detector to the target domain, and can learn transformations with or without densely labeled data in the source (e.g. semantic segmentation annotations). Without dense labels, as is the case when only detection labels are available in the source, transformations are learned using CycleGAN alignment. Otherwise, when dense labels are available we introduce a more efficient cycle-free method, which exploits pixel-level semantic labels to condition the training of the transformation network. The end task is then trained using detection box labels from the source, potentially including labels inferred on unlabeled source data. We show both that pixel-level transforms outperform prior approaches to detector domain adaptation, and that our cycle-free method outperforms prior models for unconstrained cycle-based learning of generic transformations while running 3.8 times faster. Our combined model improves on prior detection baselines by 12.5 mAP adapting from Sim 10K to Cityscapes, recovering over 50% of the missing performance between the unadapted baseline and the labeled-target upper bound. |
| Semantic Preserving Meta-Path Reduction (SPMR) |
Heterogeneous Information Network (HIN) has attracted much attention due to its wide applicability in a variety of data mining tasks, especially for tasks with multi-typed objects. A potentially large number of meta-paths can be extracted from the heterogeneous networks, providing abundant semantic knowledge. Though a variety of meta-paths can be defined, too many meta-paths are redundant. Reduction on the number of meta-paths can enhance the effectiveness since some redundant meta-paths provide interferential linkage to the task. Moreover, the reduced meta-paths can reflect the characteristic of the heterogeneous network. Previous endeavors try to reduce the number of meta-paths under the guidance of supervision information. Nevertheless, supervised information is expensive and may not always be available. In this paper, we propose a novel algorithm, SPMR (Semantic Preserving Meta-path Reduction), to reduce a set of pre-defined meta-paths in an unsupervised setting. The proposed method is able to evaluate a set of meta-paths to maximally preserve the semantics of original meta-paths after reduction. Experimental results show that SPMR can select a succinct subset of meta-paths which can achieve comparable or even better performance with fewer meta-paths. |
| Semantic Rectifying Generative Adversarial Network (SR-GAN) |
The existing Zero-Shot learning (ZSL) methods may suffer from the vague class attributes that are highly overlapped for different classes. Unlike these methods that ignore the discrimination among classes, in this paper, we propose to classify unseen image by rectifying the semantic space guided by the visual space. First, we pre-train a Semantic Rectifying Network (SRN) to rectify semantic space with a semantic loss and a rectifying loss. Then, a Semantic Rectifying Generative Adversarial Network (SR-GAN) is built to generate plausible visual feature of unseen class from both semantic feature and rectified semantic feature. To guarantee the effectiveness of rectified semantic features and synthetic visual features, a pre-reconstruction and a post reconstruction networks are proposed, which keep the consistency between visual feature and semantic feature. Experimental results demonstrate that our approach significantly outperforms the state-of-the-arts on four benchmark datasets. |
| Semantic Referee | Understanding why machine learning algorithms may fail is usually the task of the human expert that uses domain knowledge and contextual information to discover systematic shortcomings in either the data or the algorithm. In this paper, we propose a semantic referee, which is able to extract qualitative features of the errors emerging from deep machine learning frameworks and suggest corrections. The semantic referee relies on ontological reasoning about spatial knowledge in order to characterize errors in terms of their spatial relations with the environment. Using semantics, the reasoner interacts with the learning algorithm as a supervisor. In this paper, the proposed method of the interaction between a neural network classifier and a semantic referee shows how to improve the performance of semantic segmentation for satellite imagery data. |
| Semantic Role Labeling (SRL) |
In the field of artificial intelligence, Semantic role labeling, sometimes also called shallow semantic parsing, is a process in natural language processing that assigns labels to words or phrases in a sentence that indicate their semantic role in the sentence, such as that of an agent, goal, or result. It consists of the detection of the semantic arguments associated with the predicate or verb of a sentence and their classification into their specific roles. For example, given a sentence like ‘Mary sold the book to John’, the task would be to recognize the verb ‘to sell’ as representing the predicate, ‘Mary’ as representing the seller (agent), ‘the book’ as representing the goods (theme), and ‘John’ as representing the recipient. This is an important step towards making sense of the meaning of a sentence. A semantic analysis of this sort is at a lower-level of abstraction than a syntax tree, i.e. it has more categories, thus groups fewer clauses in each category. For instance, ‘the book belongs to me’ would need two labels such as ‘possessed’ and ‘possessor’ whereas ‘the book was sold to John’ would need two other labels such as ‘goal’ (or ‘theme’) and ‘receiver’ (or ‘recipient’) even though these two clauses would be very similar as far as ‘subject’ and ‘object’ functions are concerned. Towards Semi-Supervised Learning for Deep Semantic Role Labeling |
| Semantic Tagging | Semantic Tagging is the process of associating an element from an ontology with some document, usually a computer file or website. Semantic tagging serves the goal of describing a document in order to facilitate better retrieval later on. Semantic tagging also helps to integrate the tagged document with other resources that are also related to the same ontology. Semantic tagging is a special kind of annotation. What can we learn from Semantic Tagging? |
| Semantic Text Regeneration and Alignment Module | ➚ “MirrorGAN” |
| Semantic Textual Similarity (STS) |
The goal of the’ Semantic Textual Similarity (STS)’ task is to create a unified framework for the evaluation of semantic textual similarity modules and to characterize their impact on NLP applications.’ STS measures the degree of semantic equivalence. We are proposing the STS task as an attempt at creating a unified framework that allows for an extrinsic evaluation of multiple semantic components that otherwise have historically tended to be evaluated independently and without characterization of impact on NLP applications. STS is related to both Textual Entailment (TE) and – Paraphrase, but differs in a number of ways and it is more directly applicable to a number of NLP tasks. ‘ STS is ‘ different from TE inasmuch as it assumes bidirectional graded equivalence between the pair of textual snippets. In the case of TE the equivalence is directional, e.g. a car is a vehicle, but a vehicle is not necessarily a car. STS also differs from both TE and Paraphrase in that, rather than being a binary yes/no decision (e.g. a vehicle is not a car), STS is a graded similarity notion (e.g. a vehicle and a car are more similar than a wave and a car). This graded bidirectional nature of STS is useful for NLP tasks such as MT evaluation, information extraction, question answering, and summarization. Current textual similarity systems are limited in the scope of similarity they can address, mostly lexical and syntactic similarity. Some other linguistic phenomena have rarely been addressed in isolated efforts, e.g. metaphorical or idiomatic language (John spilled his guts to Mary, vs. John told Mary all about his stories/life), scoping and under-specification (Every representative of the company saw every sample), sentences where the structure is very divergent (The annihilation of Rome in 2000 BC was incurred by an insurgency of the slaves. Vs. The slaves’ revolution 2 millennia before Christ destroyed the capital of the Roman Empire.), and various modality phenomena such as committed belief, permission or negation. The STS task would like to foster joint research efforts on these, to date, fragmented areas. http://…/Thesis_Screen.pdf |
| Semantic Vector Network (SeVeN) |
We present SeVeN (Semantic Vector Networks), a hybrid resource that encodes relationships between words in the form of a graph. Different from traditional semantic networks, these relations are represented as vectors in a continuous vector space. We propose a simple pipeline for learning such relation vectors, which is based on word vector averaging in combination with an ad hoc autoencoder. We show that by explicitly encoding relational information in a dedicated vector space we can capture aspects of word meaning that are complementary to what is captured by word embeddings. For example, by examining clusters of relation vectors, we observe that relational similarities can be identified at a more abstract level than with traditional word vector differences. Finally, we test the effectiveness of semantic vector networks in two tasks: measuring word similarity and neural text categorization. SeVeN is available at bitbucket.org/luisespinosa/seven. |
| Semantic Vector Spaces (SVS) |
svs |
| Semantic View Selection | An understanding of the nature of objects could help robots to solve both high-level abstract tasks and improve performance at lower-level concrete tasks. Although deep learning has facilitated progress in image understanding, a robot’s performance in problems like object recognition often depends on the angle from which the object is observed. Traditionally, robot sorting tasks rely on a fixed top-down view of an object. By changing its viewing angle, a robot can select a more semantically informative view leading to better performance for object recognition. In this paper, we introduce the problem of semantic view selection, which seeks to find good camera poses to gain semantic knowledge about an observed object. We propose a conceptual formulation of the problem, together with a solvable relaxation based on clustering. We then present a new image dataset consisting of around 10k images representing various views of 144 objects under different poses. Finally we use this dataset to propose a first solution to the problem by training a neural network to predict a ‘semantic score’ from a top view image and camera pose. The views predicted to have higher scores are then shown to provide better clustering results than fixed top-down views. |
| Semantic Weight-Inverse Document Frequency (SW-IDF) |
Time-sync comments reveal a new way of extracting the online video tags. However, such time-sync comments have lots of noises due to users’ diverse comments, introducing great challenges for accurate and fast video tag extractions. In this paper, we propose an unsupervised video tag extraction algorithm named Semantic Weight-Inverse Document Frequency (SW-IDF). Specifically, we first generate corresponding semantic association graph (SAG) using semantic similarities and timestamps of the time-sync comments. Second, we propose two graph cluster algorithms, i.e., dialogue-based algorithm and topic center-based algorithm, to deal with the videos with different density of comments. Third, we design a graph iteration algorithm to assign the weight to each comment based on the degrees of the clustered subgraphs, which can differentiate the meaningful comments from the noises. Finally, we gain the weight of each word by combining Semantic Weight (SW) and Inverse Document Frequency (IDF). In this way, the video tags are extracted automatically in an unsupervised way. Extensive experiments have shown that SW-IDF (dialogue-based algorithm) achieves 0.4210 F1-score and 0.4932 MAP (Mean Average Precision) in high-density comments, 0.4267 F1-score and 0.3623 MAP in low-density comments; while SW-IDF (topic center-based algorithm) achieves 0.4444 F1-score and 0.5122 MAP in high-density comments, 0.4207 F1-score and 0.3522 MAP in low-density comments. It has a better performance than the state-of-the-art unsupervised algorithms in both F1-score and MAP. |
| Semantic WordRank | We present Semantic WordRank (SWR), an unsupervised method for generating an extractive summary of a single document. Built on a weighted word graph with semantic and co-occurrence edges, SWR scores sentences using an article-structure-biased PageRank algorithm with a Softplus function adjustment, and promotes topic diversity using spectral subtopic clustering under the Word-Movers-Distance metric. We evaluate SWR on the DUC-02 and SummBank datasets and show that SWR produces better summaries than the state-of-the-art algorithms over DUC-02 under common ROUGE measures. We then show that, under the same measures over SummBank, SWR outperforms each of the three human annotators (aka. judges) and compares favorably with the combined performance of all judges. |
| Semantically Aligned Bias Reducing (SABR) |
Zero shot learning (ZSL) aims to recognize unseen classes by exploiting semantic relationships between seen and unseen classes. Two major problems faced by ZSL algorithms are the hubness problem and the bias towards the seen classes. Existing ZSL methods focus on only one of these problems in the conventional and generalized ZSL setting. In this work, we propose a novel approach, Semantically Aligned Bias Reducing (SABR) ZSL, which focuses on solving both the problems. It overcomes the hubness problem by learning a latent space that preserves the semantic relationship between the labels while encoding the discriminating information about the classes. Further, we also propose ways to reduce the bias of the seen classes through a simple cross-validation process in the inductive setting and a novel weak transfer constraint in the transductive setting. Extensive experiments on three benchmark datasets suggest that the proposed model significantly outperforms existing state-of-the-art algorithms by ~1.5-9% in the conventional ZSL setting and by ~2-14% in the generalized ZSL for both the inductive and transductive settings. |
| Semantically Informed Visual Odometry and Mapping (SIVO) |
In order to facilitate long-term localization using a visual simultaneous localization and mapping (SLAM) algorithm, careful feature selection is required such that reference points persist over long durations and the runtime and storage complexity of the algorithm remain consistent. We present SIVO (Semantically Informed Visual Odometry and Mapping), a novel information-theoretic feature selection method for visual SLAM which incorporates machine learning and neural network uncertainty into the feature selection pipeline. Our algorithm selects points which provide the highest reduction in Shannon entropy between the entropy of the current state, and the joint entropy of the state given the addition of the new feature with the classification entropy of the feature from a Bayesian neural network. This feature selection strategy generates a sparse map suitable for long-term localization, as each selected feature significantly reduces the uncertainty of the vehicle state and has been detected to be a static object (building, traffic sign, etc.) repeatedly with a high confidence. The KITTI odometry dataset is used to evaluate our method, and we also compare our results against ORB_SLAM2. Overall, SIVO performs comparably to ORB_SLAM2 (average of 0.17% translation error difference, 6.2 x 10^(-5) deg/m rotation error difference) while reducing the map size by 69%. |
| Semantic-Aware DIscrete Hashing (SADIH) |
Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in large-scale multimedia retrieval applications. Particularly supervised hashing has recently received considerable research attention by leveraging the label information to preserve the pairwise similarities of data points in the Hamming space. However, there still remain two crucial bottlenecks: 1) the learning process of the full pairwise similarity preservation is computationally unaffordable and unscalable to deal with big data; 2) the available category information of data are not well-explored to learn discriminative hash functions. To overcome these challenges, we propose a unified Semantic-Aware DIscrete Hashing (SADIH) framework, which aims to directly embed the transformed semantic information into the asymmetric similarity approximation and discriminative hashing function learning. Specifically, a semantic-aware latent embedding is introduced to asymmetrically preserve the full pairwise similarities while skillfully handle the cumbersome n times n pairwise similarity matrix. Meanwhile, a semantic-aware autoencoder is developed to jointly preserve the data structures in the discriminative latent semantic space and perform data reconstruction. Moreover, an efficient alternating optimization algorithm is proposed to solve the resulting discrete optimization problem. Extensive experimental results on multiple large-scale datasets demonstrate that our SADIH can clearly outperform the state-of-the-art baselines with the additional benefit of lower computational costs. |
| Semantic-Aware Knowledge prEservation (SAKE) |
Sketch-based image retrieval (SBIR) is widely recognized as an important vision problem which implies a wide range of real-world applications. Recently, research interests arise in solving this problem under the more realistic and challenging setting of zero-shot learning. In this paper, we investigate this problem from the viewpoint of domain adaptation which we show is critical in improving feature embedding in the zero-shot scenario. Based on a framework which starts with a pre-trained model on ImageNet and fine-tunes it on the training set of SBIR benchmark, we advocate the importance of preserving previously acquired knowledge, e.g., the rich discriminative features learned from ImageNet, so as to improve the model’s transfer ability. For this purpose, we design an approach named Semantic-Aware Knowledge prEservation (SAKE), which fine-tunes the pre-trained model in an economical way and leverages semantic information, e.g., inter-class relationship, to achieve the goal of knowledge preservation. Zero-shot experiments on two extended SBIR datasets, TU-Berlin and Sketchy, verify the superior performance of our approach. Extensive diagnostic experiments validate that knowledge preserved benefits SBIR in zero-shot settings, as a large fraction of the performance gain is from the more properly structured feature embedding for photo images. |
| Semantics | The investigation of interpretations of a logical calculus (a formal axiomatic theory), of the study of the sense and meaning of constructions in formal language theory, and of the methods of understanding its logical connectives and formulas. Semantics studies the precise description and definition of such concepts as ‘truth’ , ‘definability’ , ‘denotation’ , at least in the context of a formal language. In a slightly narrower sense, by the semantics of a formalized language one means a system of agreements that determine the understanding of the formulas of the language, and that define the conditions for these formulas to be true. The semantics of logical connectives in classical and intuitionistic logic has an extensional nature: that is, the truth of a complex statement is determined only by the truth character of the expressions that form it. In other classical logics – for example, relevance logics – the meaningful content of concepts can be taken into account (such logics are called intensional). E.g., in logics of this kind not all true expressions are necessarily equivalent. |
| Semantics Guided Graph Relation Neural Network (SGRN) |
Scene graph construction / visual relationship detection from an image aims to give a precise structural description of the objects (nodes) and their relationships (edges). The mutual promotion of object detection and relationship detection is important for enhancing their individual performance. In this work, we propose a new framework, called semantics guided graph relation neural network (SGRN), for effective visual relationship detection. First, to boost the object detection accuracy, we introduce a source-target class cognoscitive transformation that transforms the features of the co-occurent objects to the target object domain to refine the visual features. Similarly, source-target cognoscitive transformations are used to refine features of objects from features of relations, and vice versa. Second, to boost the relation detection accuracy, besides the visual features of the paired objects, we embed the class probability of the object and subject separately to provide high level semantic information. In addition, to reduce the search space of relationships, we design a semantics-aware relationship filter to exclude those object pairs that have no relation. We evaluate our approach on the Visual Genome dataset and it achieves the state-of-the-art performance for visual relationship detection. Additionally, Our approach also significantly improves the object detection performance (i.e. 4.2\% in mAP accuracy). |
| Semblance | Kernel methods provide a principled approach for detecting nonlinear relations using well understood linear algorithms. In exploratory data analyses when the underlying structure of the data’s probability space is unclear, the choice of kernel is often arbitrary. Here, we present a novel kernel, Semblance, on a probability feature space. The advantage of Semblance lies in its distribution free formulation and its ability to detect niche features by placing greater emphasis on similarity between observation pairs that fall at the tail ends of a distribution, as opposed to those that fall towards the mean. We prove that Semblance is a valid Mercer kernel and illustrate its applicability through simulations and real world examples. |
| Semi-Automated Spectral Relevance Analysis | Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly ‘intelligent’ behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade games. This showcases a spectrum of problem-solving behaviors ranging from naive and short-sighted, to well-informed and strategic. We observe that standard performance evaluation metrics can be oblivious to distinguishing these diverse problem solving behaviors. Furthermore, we propose our semi-automated Spectral Relevance Analysis that provides a practically effective way of characterizing and validating the behavior of nonlinear learning machines. This helps to assess whether a learned model indeed delivers reliably for the problem that it was conceived for. Furthermore, our work intends to add a voice of caution to the ongoing excitement about machine intelligence and pledges to evaluate and judge some of these recent successes in a more nuanced manner. |
| Semi-Autoregressive Transformer (SAT) |
Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences. In this paper, we propose a novel model for fast sequence generation — the semi-autoregressive Transformer (SAT). The SAT keeps the autoregressive property in global but relieves in local and thus are able to produce multiple successive words in parallel at each time step. Experiments conducted on English-German and Chinese-English translation tasks show that the SAT achieves a good balance between translation quality and decoding speed. On WMT’14 English-German translation, the SAT achieves 5.58$\times$ speedup while maintaining 88\% translation quality, significantly better than the previous non-autoregressive methods. When produces two words at each time step, the SAT is almost lossless (only 1\% degeneration in BLEU score). |
| Semi-Cyclic Stochastic Gradient Descent | We consider convex SGD updates with a block-cyclic structure, i.e. where each cycle consists of a small number of blocks, each with many samples from a possibly different, block-specific, distribution. This situation arises, e.g., in Federated Learning where the mobile devices available for updates at different times during the day have different characteristics. We show that such block-cyclic structure can significantly deteriorate the performance of SGD, but propose a simple approach that allows prediction with the same performance guarantees as for i.i.d., non-cyclic, sampling. |
| Semidefinite Program (SDP) |
We present a novel analysis of semidefinite programs (SDPs) with positive duality gaps, i.e., different optimal values in the primal and dual problems. These SDPs are considered extremely pathological, they are often unsolvable, and they also serve as models of more general pathological convex programs. We first characterize two variable SDPs with positive gaps: we transform them into a standard form which makes the positive gap easy to recognize. The transformation is very simple, as it mostly uses elementary row operations coming from Gaussian elimination. We next show that the two variable case sheds light on larger SDPs with positive gaps: we present SDPs in any dimension in which the positive gap is certified by the same structure as in the two variable case. We analyze an important parameter, the {\em singularity degree} of the duals of our SDPs and show that it is the largest that can result in a positive gap. We complete the paper by generating a library of difficult SDPs with positive gaps (some of these SDPs have only two variables), and a computational study. |
| Semidefinite Programming (SDP) |
In semidefinite programming (SDP), some of the most commonly used pre-processing techniques for exploiting sparsity result in non-trivial numerical issues. We show that further pre-processing, based on the so called facial reduction, can resolve the issues. In computational experiments on SDP instances from the SDPLib, a benchmark, and structured instances from polynomial and binary quadratic optimisation, we show that combining the two-step pre-processing with a standard interior-point method outperforms the interior point method, with or without the traditional pre-processing, by a considerable margin. |
| Semi-Implicit Variational Inference (SIVI) |
Semi-implicit variational inference (SIVI) is introduced to expand the commonly used analytic variational distribution family, by mixing the variational parameter with a flexible distribution. This mixing distribution can assume any density function, explicit or not, as long as independent random samples can be generated via reparameterization. Not only does SIVI expand the variational family to incorporate highly flexible variational distributions, including implicit ones that have no analytic density functions, but also sandwiches the evidence lower bound (ELBO) between a lower bound and an upper bound, and further derives an asymptotically exact surrogate ELBO that is amenable to optimization via stochastic gradient ascent. With a substantially expanded variational family and a novel optimization algorithm, SIVI is shown to closely match the accuracy of MCMC in inferring the posterior in a variety of Bayesian inference tasks. |
| Semi-Levy Driven Continuous-Time GARCH (SLD-COGARCH) |
We study the class of semi-Levy driven continuous-time GARCH, denoted by SLD-COGARCH, process. The statistical properties of this process are characterized. We show that the state process of such process can be described by a random recurrence equation with the periodic random coeffcients. We establish sufficient conditions for the existence of a strictly periodically stationary solution of the state process which causes the volatility process to be strictly periodically stationary. Furthermore, it is shown that the increments with constant length of such SLD-COGARCH process are themselves a discrete-time periodically correlated (PC) process. We apply some tests to verify the PC behavior of these increments by the simulation studies. Finally, we show that how well this model fits a set of high-frequency financial data. |
| semi-MapReduce | Graph problems are troublesome when it comes to MapReduce. Typically, to be able to design algorithms that make use of the advantages of MapReduce, assumptions beyond what the model imposes, such as the {\em density} of the input graph, are required. In a recent shift, a simple and robust model of MapReduce for graph problems, where the space per machine is set to be $O(|V|)$ has attracted considerable attention. We term this model {\em semi-MapReduce}, or in short, semi-MPC, and focus on its computational power. In this short note, we show through a set of simulation methods that semi-MPC is, perhaps surprisingly, almost equivalent to the congested clique model of distributed computing. However, semi-MPC, in addition to round complexity, incorporates another practically important dimension to optimize: the number of machines. Furthermore, we show that algorithms in other distributed computing models, such as CONGEST, can be simulated to run in the same number of rounds of semiMPC while also using an optimal number of machines. We later show the implications of these simulation methods by obtaining improved algorithms for these models using the recent algorithms that have been developed. |
| Semi-Online Step (SOS) |
We consider online optimization procedures in the context of logistic regression, focusing on the Extended Kalman Filter (EKF). We introduce a second-order algorithm close to the EKF, named Semi-Online Step (SOS), for which we prove a O(log(n)) regret in the adversarial setting, paving the way to similar results for the EKF. This regret bound on SOS is the first for such parameter-free algorithm in the adversarial logistic regression. We prove for the EKF in constant dynamics a O(log(n)) regret in expectation and in the well-specified logistic regression model. |
| Semi-Orthogonal Non-Negative Matrix Factorization (semi-orthogonal NMF) |
Non-negative Matrix Factorization (NMF) is a popular clustering and dimension reduction method by decomposing a non-negative matrix into the product of two lower dimension matrices composed of basis vectors. In this paper, we propose a semi-orthogonal NMF method that enforces one of the matrices to be orthogonal with mixed signs, thereby guarantees the rank of the factorization. Our method preserves strict orthogonality by implementing the Cayley transformation to force the solution path to be exactly on the Stiefel manifold, as opposed to the approximated orthogonality solutions in existing literature. We apply a line search update scheme along with an SVD-based initialization which produces a rapid convergence of the algorithm compared to other existing approaches. In addition, we present formulations of our method to incorporate both continuous and binary design matrices. Through various simulation studies, we show that our model has an advantage over other NMF variations regarding the accuracy of the factorization, rate of convergence, and the degree of orthogonality while being computationally competitive. We also apply our method to a text-mining data on classifying triage notes, and show the effectiveness of our model in reducing classification error compared to the conventional bag-of-words model and other alternative matrix factorization approaches. |
| SemiPsm | Recent years have witnessed a surge of manipulation of public opinion and political events by malicious social media actors. These users are referred to as ‘Pathogenic Social Media (PSM)’ accounts. PSMs are key users in spreading misinformation in social media to viral proportions. These accounts can be either controlled by real users or automated bots. Identification of PSMs is thus of utmost importance for social media authorities. The burden usually falls to automatic approaches that can identify these accounts and protect social media reputation. However, lack of sufficient labeled examples for devising and training sophisticated approaches to combat these accounts is still one of the foremost challenges facing social media firms. In contrast, unlabeled data is abundant and cheap to obtain thanks to massive user-generated data. In this paper, we propose a semi-supervised causal inference PSM detection framework, SemiPsm, to compensate for the lack of labeled data. In particular, the proposed method leverages unlabeled data in the form of manifold regularization and only relies on cascade information. This is in contrast to the existing approaches that use exhaustive feature engineering (e.g., profile information, network structure, etc.). Evidence from empirical experiments on a real-world ISIS-related dataset from Twitter suggests promising results of utilizing unlabeled instances for detecting PSMs. |
| Semi-Supervised Active Clustering (SSAC) |
We propose a framework for Semi-Supervised Active Clustering framework (SSAC), where the learner is allowed to interact with a domain expert, asking whether two given instances belong to the same cluster or not. We study the query and computational complexity of clustering in this framework. We consider a setting where the expert conforms to a center-based clustering with a notion of margin. We show that there is a trade off between computational complexity and query complexity; We prove that for the case of $k$-means clustering (i.e., when the expert conforms to a solution of $k$-means), having access to relatively few such queries allows efficient solutions to otherwise NP hard problems. In particular, we provide a probabilistic polynomial-time (BPP) algorithm for clustering in this setting that asks $O\big(k^2\log k + k\log n)$ same-cluster queries and runs with time complexity $O\big(kn\log n)$ (where $k$ is the number of clusters and $n$ is the number of instances). The success of the algorithm is guaranteed for data satisfying margin conditions under which, without queries, we show that the problem is NP hard. We also prove a lower bound on the number of queries needed to have a computationally efficient clustering algorithm in this setting. Approximate Correlation Clustering Using Same-Cluster Queries |
| Semi-Supervised Conditional Generative Adversarial Network (scGAN) |
One of the frontier issues that severely hamper the development of automatic snore sound classification (ASSC) associates to the lack of sufficient supervised training data. To cope with this problem, we propose a novel data augmentation approach based on semi-supervised conditional Generative Adversarial Networks (scGANs), which aims to automatically learn a mapping strategy from a random noise space to original data distribution. The proposed approach has the capability of well synthesizing ‘realistic’ high-dimensional data, while requiring no additional annotation process. To handle the mode collapse problem of GANs, we further introduce an ensemble strategy to enhance the diversity of the generated data. The systematic experiments conducted on a widely used Munich-Passau snore sound corpus demonstrate that the scGANs-based systems can remarkably outperform other classic data augmentation systems, and are also competitive to other recently reported systems for ASSC. |
| Semi-Supervised Deep Kernel Learning (SSDKL) |
Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep kernel learning (SSDKL), a semi-supervised regression model based on minimizing predictive variance in the posterior regularization framework. SSDKL combines the hierarchical representation learning of neural networks with the probabilistic modeling capabilities of Gaussian processes. By leveraging unlabeled data, we show improvements on a diverse set of real-world regression tasks over supervised deep kernel learning and semi-supervised methods such as VAT and mean teacher adapted for regression. |
| Semi-Supervised Explicit Dialogue State Tracker (SEDST) |
The task of dialogue generation aims to automatically provide responses given previous utterances. Tracking dialogue states is an important ingredient in dialogue generation for estimating users’ intention. However, the \emph{expensive nature of state labeling} and the \emph{weak interpretability} make the dialogue state tracking a challenging problem for both task-oriented and non-task-oriented dialogue generation: For generating responses in task-oriented dialogues, state tracking is usually learned from manually annotated corpora, where the human annotation is expensive for training; for generating responses in non-task-oriented dialogues, most of existing work neglects the explicit state tracking due to the unlimited number of dialogue states. In this paper, we propose the \emph{semi-supervised explicit dialogue state tracker} (SEDST) for neural dialogue generation. To this end, our approach has two core ingredients: \emph{CopyFlowNet} and \emph{posterior regularization}. Specifically, we propose an encoder-decoder architecture, named \emph{CopyFlowNet}, to represent an explicit dialogue state with a probabilistic distribution over the vocabulary space. To optimize the training procedure, we apply a posterior regularization strategy to integrate indirect supervision. Extensive experiments conducted on both task-oriented and non-task-oriented dialogue corpora demonstrate the effectiveness of our proposed model. Moreover, we find that our proposed semi-supervised dialogue state tracker achieves a comparable performance as state-of-the-art supervised learning baselines in state tracking procedure. |
| Semi-Supervised GAN (SS-GAN) |
We introduce a new model for building conditional generative models in a semi-supervised setting to conditionally generate data given attributes by adapting the GAN framework. The proposed semi-supervised GAN (SS-GAN) model uses a pair of stacked discriminators to learn the marginal distribution of the data, and the conditional distribution of the attributes given the data respectively. In the semi-supervised setting, the marginal distribution (which is often harder to learn) is learned from the labeled + unlabeled data, and the conditional distribution is learned purely from the labeled data. Our experimental results demonstrate that this model performs significantly better compared to existing semi-supervised conditional GAN models. |
| SEmi-supervised grAph cLassification via Cautious/Active Iteration (SEAL-C/AI) |
Node classification and graph classification are two graph learning problems that predict the class label of a node and the class label of a graph respectively. A node of a graph usually represents a real-world entity, e.g., a user in a social network, or a protein in a protein-protein interaction network. In this work, we consider a more challenging but practically useful setting, in which a node itself is a graph instance. This leads to a hierarchical graph perspective which arises in many domains such as social network, biological network and document collection. For example, in a social network, a group of people with shared interests forms a user group, whereas a number of user groups are interconnected via interactions or common members. We study the node classification problem in the hierarchical graph where a `node’ is a graph instance, e.g., a user group in the above example. As labels are usually limited in real-world data, we design two novel semi-supervised solutions named \underline{SE}mi-supervised gr\underline{A}ph c\underline{L}assification via \underline{C}autious/\underline{A}ctive \underline{I}teration (or SEAL-C/AI in short). SEAL-C/AI adopt an iterative framework that takes turns to build or update two classifiers, one working at the graph instance level and the other at the hierarchical graph level. To simplify the representation of the hierarchical graph, we propose a novel supervised, self-attentive graph embedding method called SAGE, which embeds graph instances of arbitrary size into fixed-length vectors. Through experiments on synthetic data and Tencent QQ group data, we demonstrate that SEAL-C/AI not only outperform competing methods by a significant margin in terms of accuracy/Macro-F1, but also generate meaningful interpretations of the learned representations. |
| Semi-Supervised Learning | Semi-supervised learning deals with the problem of how, if possible, to take advantage of a huge amount of not classified data, to perform classification, in situations when, typically, the labelled data are few. Even though this is not always possible (it depends on how useful is to know the distribution of the unlabelled data in the inference of the labels), several algorithm have been proposed recently. A new algorithm is proposed, that under almost neccesary conditions, attains asymptotically the performance of the best theoretical rule, when the size of unlabeled data tends to infinity. The set of necessary assumptions, although reasonables, show that semi-parametric classification only works for very well conditioned problems. |
| Semi-Supervised Multimodal Hashing | Retrieving nearest neighbors across correlated data in multiple modalities, such as image-text pairs on Facebook and video-tag pairs on YouTube, has become a challenging task due to the huge amount of data. Multimodal hashing methods that embed data into binary codes can boost the retrieving speed and reduce storage requirement. As unsupervised multimodal hashing methods are usually inferior to supervised ones, while the supervised ones requires too much manually labeled data, the proposed method in this paper utilizes a part of labels to design a semi-supervised multimodal hashing method. It first computes the transformation matrices for data matrices and label matrix. Then, with these transformation matrices, fuzzy logic is introduced to estimate a label matrix for unlabeled data. Finally, it uses the estimated label matrix to learn hashing functions for data in each modality to generate a unified binary code matrix. Experiments show that the proposed semi-supervised method with 50% labels can get a medium performance among the compared supervised ones and achieve an approximate performance to the best supervised method with 90% labels. With only 10% labels, the proposed method can still compete with the worst compared supervised one. |
| Semi-Supervised Novelty Detection (SSND) |
A common setting for novelty detection assumes that labeled examples from the nominal class are available, but that labeled examples of novelties are unavailable. The standard (inductive) approach is to declare novelties where the nominal density is low, which reduces the problem to density level set estimation. In this paper, we consider the setting where an unlabeled and possibly contaminated sample is also available at learning time. We argue that novelty detection in this semi-supervised setting is naturally solved by a general reduction to a binary classification problem. In particular, a detector with a desired false positive rate can be achieved through a reduction to Neyman-Pearson classification. Unlike the inductive approach, semi-supervised novelty detection (SSND) yields detectors that are optimal (e.g., statistically consistent) regardless of the distribution on novelties. Therefore, in novelty detection, unlabeled data have a substantial impact on the theoretical properties of the decision rule. We validate the practical utility of SSND with an extensive experimental study. We also show that SSND provides distribution-free, learning-theoretic solutions to two well known problems in hypothesis testing. First, our results provide a general solution to the general two-sample problem, that is, the problem of determining whether two random samples arise from the same distribution. Second, a specialization of SSND coincides with the standard p-value approach to multiple testing under the so-called random effects model. Unlike standard rejection regions based on thresholded p-values, the general SSND framework allows for adaptation to arbitrary alternative distributions in multiple dimensions |
| Semi-Supervised Semantic Matching | Convolutional neural networks (CNNs) have been successfully applied to solve the problem of correspondence estimation between semantically related images. Due to non-availability of large training datasets, existing methods resort to self-supervised or unsupervised training paradigm. In this paper we propose a semi-supervised learning framework that imposes cyclic consistency constraint on unlabeled image pairs. Together with the supervised loss the proposed model achieves state-of-the-art on a benchmark semantic matching dataset. |
| SEmi-supervised VErification Network (SEVEN) |
Verification determines whether two samples belong to the same class or not, and has important applications such as face and fingerprint verification, where thousands or millions of categories are present but each category has scarce labeled examples, presenting two major challenges for existing deep learning models. We propose a deep semi-supervised model named SEmi-supervised VErification Network (SEVEN) to address these challenges. The model consists of two complementary components. The generative component addresses the lack of supervision within each category by learning general salient structures from a large amount of data across categories. The discriminative component exploits the learned general features to mitigate the lack of supervision within categories, and also directs the generative component to find more informative structures of the whole data manifold. The two components are tied together in SEVEN to allow an end-to-end training of the two components. Extensive experiments on four verification tasks demonstrate that SEVEN significantly outperforms other state-of-the-art deep semi-supervised techniques when labeled data are in short supply. Furthermore, SEVEN is competitive with fully supervised baselines trained with a larger amount of labeled data. It indicates the importance of the generative component in SEVEN. |
| semopy | Structural equation modelling (SEM) is a multivariate statistical technique for estimating complex relationships between observed and latent variables. Although numerous SEM packages exist, each of them has limitations. Some packages are not free or open-source; the most popular package not having this disadvantage is $\textbf{lavaan}$, but it is written in R language, which is behind current mainstream tendencies that make it harder to be incorporated into developmental pipelines (i.e. bioinformatical ones). Thus we developed the Python package $\textbf{semopy}$ to satisfy those criteria. The paper provides detailed examples of package usage and explains it’s inner clockworks. Moreover, we developed the unique generator of SEM models to extensively test SEM packages and demonstrated that $\textbf{semopy}$ significantly outperforms $\textbf{lavaan}$ in execution time and accuracy. |
| SemScale | During the last fifteen years, text scaling approaches have become a central element for the text-as-data community. However, they are based on the assumption that latent positions can be captured just by modeling word-frequency information from the different documents under study. We challenge this by presenting a new semantically aware unsupervised scaling algorithm, SemScale, which relies upon distributional representations of the documents under study. We conduct an extensive quantitative analysis over a collection of speeches from the European Parliament in five different languages and from two different legislations, in order to understand whether a) an approach that is aware of semantics would better capture known underlying political dimensions compared to a frequency-based scaling method, b) such positioning correlates in particular with a specific subset of linguistic traits, compared to the use of the entire text, and c) these findings hold across different languages. To support further research on this new branch of text scaling approaches, we release the employed dataset and evaluation setting, an easy-to-use online demo, and a Python implementation of SemScale. |
| SemTK | The relatively recent adoption of Knowledge Graphs as an enabling technology in multiple high-profile artificial intelligence and cognitive applications has led to growing interest in the Semantic Web technology stack. Many semantics-related tools, however, are focused on serving experts with a deep understanding of semantic technologies. For example, triplification of relational data is available but there is no open source tool that allows a user unfamiliar with OWL/RDF to import data into a semantic triple store in an intuitive manner. Further, many tools require users to have a working understanding of SPARQL to query data. Casual users interested in benefiting from the power of Knowledge Graphs have few tools available for exploring, querying, and managing semantic data. We present SemTK, the Semantics Toolkit, a user-friendly suite of tools that allow both expert and non-expert semantics users convenient ingestion of relational data, simplified query generation, and more. The exploration of ontologies and instance data is performed through SPARQLgraph, an intuitive web-based user interface in SemTK understandable and navigable by a lay user. The open source version of SemTK is available at http://semtk.research.ge.com. |
| SenGen | We present a new topic model that generates documents by sampling a topic for one whole sentence at a time, and generating the words in the sentence using an RNN decoder that is conditioned on the topic of the sentence. We argue that this novel formalism will help us not only visualize and model the topical discourse structure in a document better, but also potentially lead to more interpretable topics since we can now illustrate topics by sampling representative sentences instead of bag of words or phrases. We present a variational auto-encoder approach for learning in which we use a factorized variational encoder that independently models the posterior over topical mixture vectors of documents using a feed-forward network, and the posterior over topic assignments to sentences using an RNN. Our preliminary experiments on two different datasets indicate early promise, but also expose many challenges that remain to be addressed. |
| Sensitivity | Sensitivity and specificity are statistical measures of the performance of a binary classification test, also known in statistics as classification function. Sensitivity (also called the true positive rate, or the recall rate in some fields) measures the proportion of actual positives which are correctly identified as such (e.g. the percentage of sick people who are correctly identified as having the condition). Specificity (sometimes called the true negative rate) measures the proportion of negatives which are correctly identified as such (e.g. the percentage of healthy people who are correctly identified as not having the condition). These two measures are closely related to the concepts of type I and type II errors. A perfect predictor would be described as 100% sensitive (i.e. predicting all people from the sick group as sick) and 100% specific (i.e. not predicting anyone from the healthy group as sick); however, theoretically any predictor will possess a minimum error bound known as the Bayes error rate. |
| Sensitivity Analysis | Sensitivity analysis is the study of how the uncertainty in the output of a mathematical model or system (numerical or otherwise) can be apportioned to different sources of uncertainty in its inputs. A related practice is uncertainty analysis, which has a greater focus on uncertainty quantification and propagation of uncertainty. Ideally, uncertainty and sensitivity analysis should be run in tandem. Sensitivity analysis can be useful for a range of purposes, including Testing the robustness of the results of a model or system in the presence of uncertainty. Increased understanding of the relationships between input and output variables in a system or model. Uncertainty reduction: identifying model inputs that cause significant uncertainty in the output and should therefore be the focus of attention if the robustness is to be increased (perhaps by further research). Searching for errors in the model (by encountering unexpected relationships between inputs and outputs). Model simplification – fixing model inputs that have no effect on the output, or identifying and removing redundant parts of the model structure. Enhancing communication from modelers to decision makers (e.g. by making recommendations more credible, understandable, compelling or persuasive). Finding regions in the space of input factors for which the model output is either maximum or minimum or meets some optimum criterion (➚ “Optimization”, ➚ “Particle Filter”). In case of calibrating models with large number of parameters, a primary sensitivity test can ease the calibration stage by focusing on the sensitive parameters. Not knowing the sensitivity of parameters can result in time being uselessly spent on non-sensitive ones. Taking an example from economics, in any budgeting process there are always variables that are uncertain. Future tax rates, interest rates, inflation rates, headcount, operating expenses and other variables may not be known with great precision. Sensitivity analysis answers the question, ‘if these variables deviate from expectations, what will the effect be (on the business, model, system, or whatever is being analyzed), and which variables are causing the largest deviations?’ reval |
| Sensor Transformation Attention Networks | Recent work on encoder-decoder models for sequence-to-sequence mapping has shown that integrating both temporal and spatial attention mechanisms into neural networks increases the performance of the system substantially. In this work, we report on the application of an attentional signal not on temporal and spatial regions of the input, but instead as a method of switching among inputs themselves. We evaluate the particular role of attentional switching in the presence of dynamic noise in the sensors, and demonstrate how the attentional signal responds dynamically to changing noise levels in the environment to achieve increased performance on both audio and visual tasks in three commonly-used datasets: TIDIGITS, Wall Street Journal, and GRID. Moreover, the proposed sensor transformation network architecture naturally introduces a number of advantages that merit exploration, including ease of adding new sensors to existing architectures, attentional interpretability, and increased robustness in a variety of noisy environments not seen during training. Finally, we demonstrate that the sensor selection attention mechanism of a model trained only on the small TIDIGITS dataset can be transferred directly to a pre-existing larger network trained on the Wall Street Journal dataset, maintaining functionality of switching between sensors to yield a dramatic reduction of error in the presence of noise. |
| SentEval | We introduce SentEval, a toolkit for evaluating the quality of universal sentence representations. SentEval encompasses a variety of tasks, including binary and multi-class classification, natural language inference and sentence similarity. The set of tasks was selected based on what appears to be the community consensus regarding the appropriate evaluations for universal sentence representations. The toolkit comes with scripts to download and preprocess datasets, and an easy interface to evaluate sentence encoders. The aim is to provide a fairer, less cumbersome and more centralized way for evaluating sentence representations. |
| Sentic Computing | Sentic computing is a multi-disciplinary approach to natural language processing and understanding at the crossroads between affective computing, information extraction, and common-sense computing, which exploits both computer and social sciences to better interpret and process information on the Web. In sentic computing, whose term derives from the Latin ‘sentire’ (root of words such as sentiment and sentience) and ‘sensus’ (as in common-sense), the analysis of natural language is based on affective ontologies and common-sense reasoning tools, which enable the analysis of text not only at document-, page- or paragraph-level, but also at sentence-, clause-, and concept-level. In particular, sentic computing involves the use of AI and Semantic Web techniques, for knowledge representation and inference; mathematics, for carrying out tasks such as graph mining and multi-dimensionality reduction; linguistics, for discourse analysis and pragmatics; psychology, for cognitive and affective modeling; sociology, for understanding social network dynamics and social influence; finally ethics, for understanding related issues about the nature of mind and the creation of emotional machines. jumping NLP curves Sentic computing adopts the bag-of-concepts model in stead of simply counting word co-occurrence frequencies in text. Working at concept-level entails preserving the meaning carried by multi-word expressions such as ‘cloud computing’, which represent semantic atoms that should never be broken down into single words. In the bag-of-words model, for example, the concept ‘cloud computing’ would be split into ‘computing’ and ‘cloud’, which may wrongly activate concepts related to the weather and, hence, compromise categorization accuracy. http://…/sentic-computing.pdf http://…/9789400750692 |
| Sentient Enterprise | The continued explosion of data and the continued evolution of analytics capabilities might usher in the next analytics revolution beyond the Intelligent Enterprise. The evolution of analytics capabilities towards an ideal state that is called ‘The Sentient Enterprise’. The Sentient Enterprise is an enterprise that can listen to data, conduct analysis and make autonomous decisions at massive scale in real-time. The Sentient Enterprise can listen to data to sense micro-trends. It can act as one organism without being impeded by information silos. It can make autonomous decisions with little or no human intervention. It is always evolving, with emergent intelligence that becomes progressively more sophisticated. http://…/1317004 |
| Sentiment Analysis | Opinion mining (sometimes known as sentiment analysis or emotion AI) refers to the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis is widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine. Generally speaking, sentiment analysis aims to determine the attitude of a speaker, writer, or other subject with respect to some topic or the overall contextual polarity or emotional reaction to a document, interaction, or event. The attitude may be a judgment or evaluation (see appraisal theory), affective state (that is to say, the emotional state of the author or speaker), or the intended emotional communication (that is to say, the emotional effect intended by the author or interlocutor). |
| Sentiment Multi-View Variational Autoencoder (SentiVAE) |
When assigning quantitative labels to a dataset, different methodologies may rely on different scales. In particular, when assigning polarities to words in a sentiment lexicon, annotators may use binary, categorical, or continuous labels. Naturally, it is of interest to unify these labels from disparate scales to both achieve maximal coverage over words and to create a single, more robust sentiment lexicon while retaining scale coherence. We introduce a generative model of sentiment lexica to combine disparate scales into a common latent representation. We realize this model with a novel multi-view variational autoencoder (VAE), called SentiVAE. We evaluate our approach via a downstream text classification task involving nine English-Language sentiment analysis datasets; our representation outperforms six individual sentiment lexica, as well as a straightforward combination thereof. |
| Seq2Biseq | During the last couple of years, Recurrent Neural Networks (RNN) have reached state-of-the-art performances on most of the sequence modelling problems. In particular, the ‘sequence to sequence’ model and the neural CRF have proved to be very effective in this domain. In this article, we propose a new RNN architecture for sequence labelling, leveraging gated recurrent layers to take arbitrarily long contexts into account, and using two decoders operating forward and backward. We compare several variants of the proposed solution and their performances to the state-of-the-art. Most of our results are better than the state-of-the-art or very close to it and thanks to the use of recent technologies, our architecture can scale on corpora larger than those used in this work. |
| seq2graph | Discovering temporal lagged and inter-dependencies in multivariate time series data is an important task. However, in many real-world applications, such as commercial cloud management, manufacturing predictive maintenance, and portfolios performance analysis, such dependencies can be non-linear and time-variant, which makes it more challenging to extract such dependencies through traditional methods such as Granger causality or clustering. In this work, we present a novel deep learning model that uses multiple layers of customized gated recurrent units (GRUs) for discovering both time lagged behaviors as well as inter-timeseries dependencies in the form of directed weighted graphs. We introduce a key component of Dual-purpose recurrent neural network that decodes information in the temporal domain to discover lagged dependencies within each time series, and encodes them into a set of vectors which, collected from all component time series, form the informative inputs to discover inter-dependencies. Though the discovery of two types of dependencies are separated at different hierarchical levels, they are tightly connected and jointly trained in an end-to-end manner. With this joint training, learning of one type of dependency immediately impacts the learning of the other one, leading to overall accurate dependencies discovery. We empirically test our model on synthetic time series data in which the exact form of (non-linear) dependencies is known. We also evaluate its performance on two real-world applications, (i) performance monitoring data from a commercial cloud provider, which exhibit highly dynamic, non-linear, and volatile behavior and, (ii) sensor data from a manufacturing plant. We further show how our approach is able to capture these dependency behaviors via intuitive and interpretable dependency graphs and use them to generate highly accurate forecasts. |
| Seq2Seq | Multi-label text classification (MLTC) aims to assign multiple labels to each sample in the dataset. The labels usually have internal correlations. However, traditional methods tend to ignore the correlations between labels. In order to capture the correlations between labels, the sequence-to-sequence (Seq2Seq) model views the MLTC task as a sequence generation problem, which achieves excellent performance on this task. However, the Seq2Seq model is not suitable for the MLTC task in essence. The reason is that it requires humans to predefine the order of the output labels, while some of the output labels in the MLTC task are essentially an unordered set rather than an ordered sequence. This conflicts with the strict requirement of the Seq2Seq model for the label order. In this paper, we propose a novel sequence-to-set framework utilizing deep reinforcement learning, which not only captures the correlations between labels, but also reduces the dependence on the label order. Extensive experimental results show that our proposed method outperforms the competitive baselines by a large margin. |
| Seq2Seq2Sentiment | Multimodal machine learning is a core research area spanning the language, visual and acoustic modalities. The central challenge in multimodal learning involves learning representations that can process and relate information from multiple modalities. In this paper, we propose two methods for unsupervised learning of joint multimodal representations using sequence to sequence (Seq2Seq) methods: a \textit{Seq2Seq Modality Translation Model} and a \textit{Hierarchical Seq2Seq Modality Translation Model}. We also explore multiple different variations on the multimodal inputs and outputs of these seq2seq models. Our experiments on multimodal sentiment analysis using the CMU-MOSI dataset indicate that our methods learn informative multimodal representations that outperform the baselines and achieve improved performance on multimodal sentiment analysis, specifically in the Bimodal case where our model is able to improve F1 Score by twelve points. We also discuss future directions for multimodal Seq2Seq methods. |
| Seq2Slate | Ranking is a central task in machine learning and information retrieval. In this task, it is especially important to present the user with a slate of items that is appealing as a whole. This in turn requires taking into account interactions between items, since intuitively, placing an item on the slate affects the decision of which other items should be placed alongside it. In this work, we propose a sequence-to-sequence model for ranking called seq2slate. At each step, the model predicts the next item to place on the slate given the items already selected. The recurrent nature of the model allows complex dependencies between items to be captured directly in a flexible and scalable way. We show how to learn the model end-to-end from weak supervision in the form of easily obtained click-through data. We further demonstrate the usefulness of our approach in experiments on standard ranking benchmarks as well as in a real-world recommendation system. |
| Seq2SQL | Relational databases store a significant amount of the worlds data. However, accessing this data currently requires users to understand a query language such as SQL. We propose Seq2SQL, a deep neural network for translating natural language questions to corresponding SQL queries. Our model uses rewards from inthe- loop query execution over the database to learn a policy to generate the query, which contains unordered parts that are less suitable for optimization via cross entropy loss. Moreover, Seq2SQL leverages the structure of SQL to prune the space of generated queries and significantly simplify the generation problem. In addition to the model, we release WikiSQL, a dataset of 80654 hand-annotated examples of questions and SQL queries distributed across 24241 tables fromWikipedia that is an order of magnitude larger than comparable datasets. By applying policybased reinforcement learning with a query execution environment to WikiSQL, Seq2SQL outperforms a state-of-the-art semantic parser, improving execution accuracy from 35.9% to 59.4% and logical form accuracy from 23.4% to 48.3%. |
| Sequence and Set Similarity Measure (S3M) |
In many data mining applications, both classification and clustering algorithms require a distance/similarity measure. The central problem in similarity based clustering/classification comprising sequential data is deciding an appropriate similarity metric. The existing metrics like Euclidean, Jaccard, Cosine, and so forth do not exploit the sequential nature of data explicitly. In this paper, the authors propose a similarity preserving function called Sequence and Set Similarity Measure (S3M) that captures both the order of occurrence of items in sequences and the constituent items of sequences. |
| Sequence Graph Transform (SGT) |
A ubiquitous presence of sequence data across fields, like, web, healthcare, bioinformatics, text mining, etc., has made sequence mining a vital research area. However, sequence mining is particularly challenging because of absence of an accurate and fast approach to find (dis)similarity between sequences. As a measure of (dis)similarity, mainstream data mining methods like k-means, kNN, regression, etc., have proved distance between data points in a euclidean space to be most effective. But a distance measure between sequences is not obvious due to their unstructuredness — arbitrary strings of arbitrary length. We, therefore, propose a new function, called as Sequence Graph Transform (SGT), that extracts sequence features and embeds it in a finite-dimensional euclidean space. It is scalable due to a low computational complexity and has a universal applicability on any sequence problem. We theoretically show that SGT can capture both short and long patterns in sequences, and provides an accurate distance-based measure of (dis)similarity between them. This is also validated experimentally. Finally, we show its real world application for clustering, classification, search and visualization on different sequence problems. |
| Sequence Mixed Graphs (SMG) |
A mixed graph can be seen as a type of digraph containing some edges (two opposite arcs). Here we introduce the concept of sequence mixed graphs, which is a generalization of both sequence graphs and iterated line digraphs. These structures are proven to be useful in the problem of constructing dense graphs or digraphs, and this is related to the degree/diameter problem. Thus, our generalized approach gives rise to graphs that have also good ratio order/diameter. Moreover, we propose a general method for obtaining a sequence mixed digraph by identifying some vertices of a certain iterated line digraph. As a consequence, some results about distance-related parameters (mainly, the diameter and the average distance) of sequence mixed graphs are presented. |
| Sequenced-Replacement Sampling (SRS) |
We propose sequenced-replacement sampling (SRS) for training deep neural networks. The basic idea is to assign a fixed sequence index to each sample in the dataset. Once a mini-batch is randomly drawn in each training iteration, we refill the original dataset by successively adding samples according to their sequence index. Thus we carry out replacement sampling but in a batched and sequenced way. In a sense, SRS could be viewed as a way of performing ‘mini-batch augmentation’. It is particularly useful for a task where we have a relatively small images-per-class such as CIFAR-100. Together with a longer period of initial large learning rate, it significantly improves the classification accuracy in CIFAR-100 over the current state-of-the-art results. Our experiments indicate that training deeper networks with SRS is less prone to over-fitting. In the best case, we achieve an error rate as low as 10.10%. |
| Sequence-to-Sequence-to-Sequence Autoencoder (SEQ^3) |
Neural sequence-to-sequence models are currently the dominant approach in several natural language processing tasks, but require large parallel corpora. We present a sequence-to-sequence-to-sequence autoencoder (SEQ^3), consisting of two chained encoder-decoder pairs, with words used as a sequence of discrete latent variables. We apply the proposed model to unsupervised abstractive sentence compression, where the first and last sequences are the input and reconstructed sentences, respectively, while the middle sequence is the compressed sentence. Constraining the length of the latent word sequences forces the model to distill important information from the input. A pretrained language model, acting as a prior over the latent sequences, encourages the compressed sentences to be human-readable. Continuous relaxations enable us to sample from categorical distributions, allowing gradient-based optimization, unlike alternatives that rely on reinforcement learning. The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets. |
| Sequential Adaptive Nonlinear Modeling of Vector Time Series (SLANTS) |
We propose a method for adaptive nonlinear sequential modeling of vector-time series data. Data is modeled as a nonlinear function of past values corrupted by noise, and the underlying non-linear function is assumed to be approximately expandable in a spline basis. We cast the modeling of data as finding a good fit representation in the linear span of multi-dimensional spline basis, and use a variant of l1-penalty regularization in order to reduce the dimensionality of representation. Using adaptive filtering techniques, we design our online algorithm to automatically tune the underlying parameters based on the minimization of the regularized sequential prediction error. We demonstrate the generality and flexibility of the proposed approach on both synthetic and real-world datasets. Moreover, we analytically investigate the performance of our algorithm by obtaining both bounds of the prediction errors, and consistency results for variable selection. |
| Sequential Analysis | In statistics, sequential analysis or sequential hypothesis testing is statistical analysis where the sample size is not fixed in advance. Instead data is evaluated as it is collected, and further sampling is stopped in accordance with a pre-defined stopping rule as soon as significant results are observed. Thus a conclusion may sometimes be reached at a much earlier stage than would be possible with more classical hypothesis testing or estimation, at consequently lower financial and/or human cost. |
| Sequential Association Rule Mining That can Extract Hierarchical Structure of Tasks in Reinforcement Learning (SARM-HSTRL) |
Reinforcement learning (RL) techniques, while often powerful, can suffer from slow learning speeds, particularly in high dimensional spaces. Decomposition of tasks into a hierarchical structure holds the potential to significantly speed up learning, generalization, and transfer learning. However, the current task decomposition techniques often rely on high-level knowledge provided by an expert (e.g. using dynamic Bayesian networks) to extract a hierarchical task structure; which is not necessarily available in autonomous systems. In this paper, we propose a novel method based on Sequential Association Rule Mining that can extract Hierarchical Structure of Tasks in Reinforcement Learning (SARM-HSTRL) in an autonomous manner for both Markov decision processes (MDPs) and factored MDPs. The proposed method leverages association rule mining to discover the causal and temporal relationships among states in different trajectories, and extracts a task hierarchy that captures these relationships among sub-goals as termination conditions of different sub-tasks. We prove that the extracted hierarchical policy offers a hierarchically optimal policy in MDPs and factored MDPs. It should be noted that SARM-HSTRL extracts this hierarchical optimal policy without having dynamic Bayesian networks in scenarios with a single task trajectory and also with multiple tasks’ trajectories. Furthermore, it has been theoretically and empirically shown that the extracted hierarchical task structure is consistent with trajectories and provides the most efficient, reliable, and compact structure under appropriate assumptions. The numerical results compare the performance of the proposed SARM-HSTRL method with conventional HRL algorithms in terms of the accuracy in detecting the sub-goals, the validity of the extracted hierarchies, and the speed of learning in several testbeds. |
| Sequential Attention Relational Network (SARN) |
This paper proposes an attention module augmented relational network called SARN (Sequential Attention Relational Network) that can carry out relational reasoning by extracting reference objects and making efficient pairing between objects. SARN greatly reduces the computational and memory requirements of the relational network, which computes all object pairs. It also shows high accuracy on the Sort-of-CLEVR dataset compared to other models, especially on relational questions. |
| Sequential Backward Selection (SBS) |
The Sequential Backward Selection (SBS) algorithm is very similar to the Sequential Fortward Selection (SFS). The only difference is that we start with the complete feature set instead of the “null set” and remove features sequentially until we reach the number of desired features k. Note that features are never added back once they were removed, which (similar to SFS) is one of the biggest downsides of this algorithm. |
| Sequential Bagging on Regression (SQB) |
Methodology: Remove one observation. Training the rest of data that are sampled without replacement and given this observation’s input, predict the response back. Replicate this N times and for each response, take a sample from these replicates with replacement. Average each responses of sample and again replicate this step N time for each observation. Approximate these N new responses and generate another N responses y’. Training these y’ and predict to have N responses of each testing observation. The average of N is the final prediction. Each observation will do the same. SQB |
| Sequential Bayesian Additive Regression Trees (sBART) |
➚ “Bayesian Additive Regression Tree” sbart |
| Sequential Convex Programming | ➚ “linearized Gaussian Process” |
| Sequential Copying Network (SeqCopyNet) |
Copying mechanism shows effectiveness in sequence-to-sequence based neural network models for text generation tasks, such as abstractive sentence summarization and question generation. However, existing works on modeling copying or pointing mechanism only considers single word copying from the source sentences. In this paper, we propose a novel copying framework, named Sequential Copying Networks (SeqCopyNet), which not only learns to copy single words, but also copies sequences from the input sentence. It leverages the pointer networks to explicitly select a sub-span from the source side to target side, and integrates this sequential copying mechanism to the generation process in the encoder-decoder paradigm. Experiments on abstractive sentence summarization and question generation tasks show that the proposed SeqCopyNet can copy meaningful spans and outperforms the baseline models. |
| Sequential Deactivation (SDA) |
We introduce a new neural network model, together with a tractable and monotone online learning algorithm. Our model describes feed-forward networks for classification, with one output node for each class. The only nonlinear operation is rectification using a ReLU function with a bias. However, there is a rectifier on every edge rather than at the nodes of the network. There are also weights, but these are positive, static, and associated with the nodes. Our ‘rectified wire’ networks are able to represent arbitrary Boolean functions. Only the bias parameters, on the edges of the network, are learned. Another departure in our approach, from standard neural networks, is that the loss function is replaced by a constraint. This constraint is simply that the value of the output node associated with the correct class should be zero. Our model has the property that the exact norm-minimizing parameter update, required to correctly classify a training item, is the solution to a quadratic program that can be computed with a few passes through the network. We demonstrate a training algorithm using this update, called sequential deactivation (SDA), on MNIST and some synthetic datasets. Upon adopting a natural choice for the nodal weights, SDA has no hyperparameters other than those describing the network structure. Our experiments explore behavior with respect to network size and depth in a family of sparse expander networks. |
| Sequential Dynamical System (SDS) |
Sequential dynamical systems (SDSs) are a class of graph dynamical systems. They are discrete dynamical systems which generalize many aspects of for example classical cellular automata, and they provide a framework for studying asynchronous processes over graphs. The analysis of SDSs uses techniques from combinatorics, abstract algebra, graph theory, dynamical systems and probability theory. |
| Sequential Embedding induced Dirichlet Process Mixture Model (SiDPMM) |
Current state-of-the-art nonparametric Bayesian text clustering methods model documents through multinomial distribution on bags of words. Although these methods can effectively utilize the word burstiness representation of documents and achieve decent performance, they do not explore the sequential information of text and relationships among synonyms. In this paper, the documents are modeled as the joint of bags of words, sequential features and word embeddings. We proposed Sequential Embedding induced Dirichlet Process Mixture Model (SiDPMM) to effectively exploit this joint document representation in text clustering. The sequential features are extracted by the encoder-decoder component. Word embeddings produced by the continuous-bag-of-words (CBOW) model are introduced to handle synonyms. Experimental results demonstrate the benefits of our model in two major aspects: 1) improved performance across multiple diverse text datasets in terms of the normalized mutual information (NMI); 2) more accurate inference of ground truth cluster numbers with regularization effect on tiny outlier clusters. |
| Sequential Floating Backward Selection (SFBS) |
Just as in the Sequential Floating Forward Selection (SFFS) algorithm, we have a conditional step: Here, we start with the whole feature subset and exclude features sequentially. Only if adding one of the previously excluded features back to a new feature subset improves the performance (assessed by the criterion function), we add it back in the Conditional Inclusion step. |
| Sequential Floating Forward Selection (SFFS) |
The Sequential Floating Forward Selection (SFFS) algorithm can be considered as extension of the simpler Sequential Fortward Selection (SFS) algorithm. In constrast to SFS, the SFFS algorithm can remove features once they were included, so that a larger number of feature subset combinations can be sampled. It is important to emphasize that the removal of included features is conditional, which makes it different from the +L -R algorithm. The Conditional Exclusion in SFFS only occurs if the resulting feature subset is assessed as “better” by the criterion function after removal of a particular feature. |
| Sequential Forward Selection (SFS) |
The Sequential Fortward Selection (SFS) is one of the simplest and probably fastest Feature Selection algorithms. Let’s summarize its mechanics in words: SFS starts with an empty feature subset and sequentially adds features from the whole input feature space to this subset until the subset reaches a desired (user-specified) size. For every iteration (= inclusion of a new feature), the whole feature subset is evaluated (expect for the features that are already included in the new subset). The evaluation is done by the so-called criterion function which assesses the feature that leads to the maximum performance improvement of the feature subset if it is included. Note that included features are never removed, which is one of the biggest downsides of this algorithm. |
| Sequential Input Selection Algorithm (SISAL) |
In time series prediction, making accurate predictions is often the primary goal. At the same time, interpretability of the models would be desirable. For the latter goal, we have devised a sequential input selection algorithm (SISAL) to choose a parsimonious, or sparse, set of input variables. Our proposed algorithm is a sequential backward selection type algorithm based on a cross-validation resampling procedure. Our strategy is to use a filter approach in the prediction: first we select a sparse set of inputs using linear models and then the selected inputs are used in the nonlinear prediction conducted with multilayer-perceptron networks. Furthermore, we perform a sensitivity analysis by quantifying the importance of the individual input variables in the nonlinear models using a method based on partial derivatives. Experiments are done with the Santa Fe laser data set that exhibits very nonlinear behavior and a data set in a problem of electricity load prediction. The results in the prediction problems of varying difficulty highlight the range of applicability of our proposed algorithm. In summary, our SISAL yields accurate and parsimonious prediction models giving insight to the original problem. sisal |
| Sequential Match Network | We study response selection for multi-turn conversation in retrieval based chatbots. Existing works either ignores relationships among utterances, or misses important information in context when matching a response with a highly abstract context vector finally. We propose a new session based matching model to address both problems. The model first matches a response with each utterance on multiple granularities, and distills important matching information from each pair as a vector with convolution and pooling operations. The vectors are then accumulated in a chronological order through a recurrent neural network (RNN) which models the relationships among the utterances. The final matching score is calculated with the hidden states of the RNN. Empirical study on two public data sets shows that our model can significantly outperform the state-of-the-art methods for response selection in multi-turn conversation. |
| Sequential Monte Carlo (SMC) |
A core problem in statistics and probabilistic machine learning is to compute probability distributions and expectations. This is the fundamental problem of Bayesian statistics and machine learning, which frames all inference as expectations with respect to the posterior distribution. The key challenge is to approximate these intractable expectations. In this tutorial, we review sequential Monte Carlo (SMC), a random-sampling-based class of methods for approximate inference. First, we explain the basics of SMC, discuss practical issues, and review theoretical results. We then examine two of the main user design choices: the proposal distributions and the so called intermediate target distributions. We review recent results on how variational inference and amortization can be used to learn efficient proposals and target distributions. Next, we discuss the SMC estimate of the normalizing constant, how this can be used for pseudo-marginal inference and inference evaluation. Throughout the tutorial we illustrate the use of SMC on various models commonly used in machine learning, such as stochastic recurrent neural networks, probabilistic graphical models, and probabilistic programs. |
| Sequential Multinomial Logit | Motivated by the phenomenon that companies introduce new products to keep abreast with customers’ rapidly changing tastes, we consider a novel online learning setting where a profit-maximizing seller needs to learn customers’ preferences through offering recommendations, which may contain existing products and new products that are launched in the middle of a selling period. We propose a sequential multinomial logit (SMNL) model to characterize customers’ behavior when product recommendations are presented in tiers. For the offline version with known customers’ preferences, we propose a polynomial-time algorithm and characterize the properties of the optimal tiered product recommendation. For the online problem, we propose a learning algorithm and quantify its regret bound. Moreover, we extend the setting to incorporate a constraint which ensures every new product is learned to a given accuracy. Our results demonstrate the tier structure can be used to mitigate the risks associated with learning new products. |
| Sequential Network Transfer | We study the problem of adapting neural sentence embedding models to the domain of human activities to capture their relations in different dimensions. We introduce a novel approach, Sequential Network Transfer, and show that it largely improves the performance on all dimensions. We also extend this approach to other semantic similarity datasets, and show that the resulting embeddings outperform traditional transfer learning approaches in many cases, achieving state-of-the-art results on the Semantic Textual Similarity (STS) Benchmark. To account for the improvements, we provide some interpretation of what the networks have learned. Our results suggest that Sequential Network Transfer is highly effective for various sentence embedding models and tasks. |
| Sequential Offsetted Regression (SOR) |
SOR |
| Sequential Parameter Optimization Toolbox (SPOT) |
The performance of optimization algorithms relies crucially on their parameterizations. Finding good parameter settings is called algorithm tuning. Using a simple simulated annealing algorithm, we will demonstrate how optimization algorithms can be tuned using the sequential parameter optimization toolbox (SPOT). SPOT provides several tools for automated and interactive tuning. The underling concepts of the SPOT approach are explained. This includes key techniques such as exploratory fitness landscape analysis and response surface methodology. Many examples illustrate how SPOT can be used for understanding the performance of algorithms and gaining insight into algorithm’s behavior. Furthermore, we demonstrate how SPOT can be used as an optimizer and how a sophisticated ensemble approach is able to combine several meta models via stacking. |
| Sequential PAttern Discovery using Equivalence classes (SPADE) |
In this paper we present SPADE, a new algorithm for fast discovery of Sequential Patterns. The existing solutions to this problem make repeated database scans, and use complex hash structures which have poor locality. SPADE utilizes combinatorial properties to decompose the original problem into smaller sub-problems, that can be independently solved in main-memory using efficient lattice search techniques, and using simple join operations. All sequences are discovered in only three database scans. Experiments showthat SPADE outperforms the best previous algorithm by a factor of two, and by an order of magnitude with some pre-processed data. It also has linear scalability with respect to the number of input-sequences, and a number of other database parameters. http://…/SPADE |
| Sequential Pattern Mining | Sequential Pattern mining is a topic of data mining concerned with finding statistically relevant patterns between data examples where the values are delivered in a sequence. It is usually presumed that the values are discrete, and thus time series mining is closely related, but usually considered a different activity. Sequential pattern mining is a special case of structured data mining. There are several key traditional computational problems addressed within this field. These include building efficient databases and indexes for sequence information, extracting the frequently occurring patterns, comparing sequences for similarity, and recovering missing sequence members. In general, sequence mining problems can be classified as string mining which is typically based on string processing algorithms and itemset mining which is typically based on association rule learning. |
| Sequential Principal Curves Analysis (SPCA) |
This work includes all the technical details of the Sequential Principal Curves Analysis (SPCA) in a single document. SPCA is an unsupervised nonlinear and invertible feature extraction technique. The identified curvilinear features can be interpreted as a set of nonlinear sensors: the response of each sensor is the projection onto the corresponding feature. Moreover, it can be easily tuned for different optimization criteria; e.g. infomax, error minimization, decorrelation; by choosing the right way to measure distances along each curvilinear feature. Even though proposed in and shown to work in multiple modalities in , the SPCA framework has its original roots in the nonlinear ICA algorithm in. Later on, the SPCA philosophy for nonlinear generalization of PCA originated substantially faster alternatives at the cost of introducing different constraints in the model. Namely, the Principal Polynomial Analysis (PPA) , and the Dimensionality Reduction via Regression (DRR). This report illustrates the reasons why we developed such family and is the appropriate technical companion for the missing details in. |
| Sequential Probability Distribution | fanplot |
| Sequential Probability Ratio Test (SPRT) |
The sequential probability ratio test (SPRT) is a specific sequential hypothesis test, developed by Abraham Wald. Neyman and Pearson’s 1933 result inspired Wald to reformulate it as a sequential analysis problem. The Neyman-Pearson lemma, by contrast, offers a rule of thumb for when all the data is collected (and its likelihood ratio known). While originally developed for use in quality control studies in the realm of manufacturing, SPRT has been formulated for use in the computerized testing of human examinees as a termination criterion. SPRT |
| Sequential Randomized Trial (SRT) |
Randomized experiments ensure robust causal inference that are critical to effective learning analytics research and practice. However, traditional randomized experiments, like A/B tests, are limiting in large scale digital learning environments. While traditional experiments can accurately compare two treatment options, they are less able to inform how to adapt interventions to continually meet learners’ diverse needs. In this work, we introduce a trial design for developing adaptive interventions in scaled digital learning environments — the sequential randomized trial (SRT). With the goal of improving learner experience and developing interventions that benefit all learners at all times, SRTs inform how to sequence, time, and personalize interventions. In this paper, we provide an overview of SRTs, and we illustrate the advantages they hold compared to traditional experiments. We describe a novel SRT run in a large scale data science MOOC. The trial results contextualize how learner engagement can be addressed through inclusive culturally targeted reminder emails. We also provide practical advice for researchers who aim to run their own SRTs to develop adaptive interventions in scaled digital learning environments. |
| Sequential Selection Problem (SSP) |
In the Sequential Selection Problem (SSP), immediate and irrevocable decisions need to be made while candidates from a finite set are being examined one-by-one. The goal is to assign a limited number of $b$ available jobs to the best possible candidates. Standard SSP variants begin with an empty selection set (cold-starting) and perform the selection process once (single-round), over a single candidate set. The Multi-Round Sequential Selection Problem |
| Sequential Set Generation (SSG) |
Consider a general machine learning setting where the output is a set of labels or sequences. This output set is unordered and its size varies with the input. Whereas multi-label classification methods seem a natural first resort, they are not readily applicable to set-valued outputs because of the growth rate of the output space; and because conventional sequence generation doesn’t reflect sets’ order-free nature. In this paper, we propose a unified framework–sequential set generation (SSG)–that can handle output sets of labels and sequences. SSG is a meta-algorithm that leverages any probabilistic learning method for label or sequence prediction, but employs a proper regularization such that a new label or sequence is generated repeatedly until the full set is produced. Though SSG is sequential in nature, it does not penalize the ordering of the appearance of the set elements and can be applied to a variety of set output problems, such as a set of classification labels or sequences. We perform experiments with both benchmark and synthetic data sets and demonstrate SSG’s strong performance over baseline methods. |
| Sequential Subspace Changepoint Detection | We consider the sequential changepoint detection problem of detecting changes that are characterized by a subspace structure which is manifested in the covariance matrix. In particular, the covariance structure changes from an identity matrix to an unknown spiked covariance model. We consider three sequential changepoint detection procedures: The exact cumulative sum (CUSUM) that assumes knowledge of all parameters, the largest eigenvalue procedure and a novel Subspace-CUSUM algorithm with the last two being used for the case when unknown parameters are present. By leveraging the extreme eigenvalue distribution from random matrix theory and modeling the non-negligible temporal correlation in the sequence of detection statistics due to the sliding window approach, we provide theoretical approximations to the average run length (ARL) and the expected detection delay (EDD) for the largest eigenvalue procedure. The three methods are compared to each other using simulations. |
| SEquential Subspace OPtimization (SESOP) |
A merger of two optimization frameworks is introduced: SEquential Subspace OPtimization (SESOP) with the MultiGrid (MG) optimization. At each iteration of the combined algorithm, search directions implied by the coarse-grid correction process of MG are added to the low dimensional search-spaces of SESOP, which include the (preconditioned) gradient and search directions involving the previous iterates (so-called history). The resulting accelerated technique is called SESOP-MG. The {\color{black} asymptotic convergence rate} of the two-level version of SESOP-MG (dubbed SESOP-TG) is studied via Fourier mode analysis for linear problems (i.e., optimization of quadratic functionals). Numerical tests on linear and nonlinear {\color{black} problems} demonstrate the effectiveness of the approach. |
| Sequential Subspace Optimization Boosting (SEBOOST) |
We present SEBOOST, a technique for boosting the performance of existing stochastic optimization methods. SEBOOST applies a secondary optimization process in the subspace spanned by the last steps and descent directions. The method was inspired by the SESOP optimization method for large-scale problems, and has been adapted for the stochastic learning framework. It can be applied on top of any existing optimization method with no need to tweak the internal algorithm. We show that the method is able to boost the performance of different algorithms, and make them more robust to changes in their hyper-parameters. As the boosting steps of SEBOOST are applied between large sets of descent steps, the additional subspace optimization hardly increases the overall computational burden. We introduce two hyper-parameters that control the balance between the baseline method and the secondary optimization process. The method was evaluated on several deep learning tasks, demonstrating promising results. |
| Sequeval | In this paper, we present sequeval, a software tool capable of performing the offline evaluation of a recommender system designed to suggest a sequence of items. A sequence-based recommender is trained considering the sequences already available in the system and its purpose is to generate a personalized sequence starting from an initial seed. This tool automatically evaluates the sequence-based recommender considering a comprehensive set of eight different metrics adapted to the sequential scenario. sequeval has been developed following the best practices of software extensibility. For this reason, it is possible to easily integrate and evaluate novel recommendation techniques. sequeval is publicly available as an open source tool and it aims to become a focal point for the community to assess sequence-based recommender systems. |
| Serial Correlation | ➚ “Autocorrelation” |
| Serial Dependence Diagrams (SDD) |
SDD |
| SERKET | To realize human-like robot intelligence, a large-scale cognitive architecture is required for robots to understand the environment through a variety of sensors with which they are equipped. In this paper, we propose a novel framework named Serket that enables the construction of a large-scale generative model and its inference easily by connecting sub-modules to allow the robots to acquire various capabilities through interaction with their environments and others. We consider that large-scale cognitive models can be constructed by connecting smaller fundamental models hierarchically while maintaining their programmatic independence. Moreover, connected modules are dependent on each other, and parameters are required to be optimized as a whole. Conventionally, the equations for parameter estimation have to be derived and implemented depending on the models. However, it becomes harder to derive and implement those of a larger scale model. To solve these problems, in this paper, we propose a method for parameter estimation by communicating the minimal parameters between various modules while maintaining their programmatic independence. Therefore, Serket makes it easy to construct large-scale models and estimate their parameters via the connection of modules. Experimental results demonstrated that the model can be constructed by connecting modules, the parameters can be optimized as a whole, and they are comparable with the original models that we have proposed. |
| Service Mining | Traditional service marketing and service science attempted to help companies understand what customers think and how companies dealt with problems. However, a holistic framework and viewpoint to explore services differently is needed. Service mining provides a different perspective into the services industry. Professionals and practitioners also need various mindsets to investigate and analyze the evidence from services. According to the concept of service science, certain areas are involved such as economics, management, computer science, and engineering. This book provides a novel concept to combine the areas of social science and computer science in services. Service mining is a holistic concept covering a service’s lifecycle from design, experience, recover to retain. Traditionally, the value of mining is to discover unknown and potential patterns from big data. Service mining focuses on the amount of data generated from the value co-creation process and features of services. The goal of service mining is to analyze any step in the service’s lifecycle and help enterprises reexamine each one. Companies can also utilize appropriate marketing or management methods to adjust biases and revise the errors of services. Service mining is defined as ‘a systematical process including service discovery, service experience, service recovery and service retention to discover unique patterns and exceptional values within the existing service pool’. The goal of service mining is similar to data mining, text mining or web mining. All aim to ‘detect something new’ from the base being mined. Service mining targets the service pool. What distinguishes service mining from data or text mining is the concept service itself. Data is generally considered factual; text, though more nuanced in that words carry connotations, has a primary denotative quality which conveys meaning that text miners and the consumers of the mined text agree upon. Service, however, is trickier. It is a process of establishing a value proposition; and the value it represents is the joint creation of the provider and the customer, each of which offers a different perception in constructing the value proposition. Moreover, in the concept of service mining, the mining target is not only the traditional categories of services but also IT-based services. Under the big umbrella of service science, service mining is considered to be a branch of it. |
| Service Science, Management, and Engineering | Service science, management, and engineering (SSME) is a term introduced by IBM to describe service science, an interdisciplinary approach to the study, design, and implementation of service systems – complex systems in which specific arrangements of people and technologies take actions that provide value for others. More precisely, SSME has been defined as the application of science, management, and engineering disciplines to tasks that one organization beneficially performs for and with another. Today, SSME is a call for academia, industry, and governments to focus on becoming more systematic about innovation in the service sector, which is the largest sector of the economy in most industrialized nations, and is fast becoming the largest sector in developing nations as well. SSME is also a proposed academic discipline and research area that would complement – rather than replace – the many disciplines that contribute to knowledge about service. The interdisciplinary nature of the field calls for a curriculum and competencies to advance the development and contribution of the field of SSME. |
| Service With Delay Problem | In this paper, we introduce the online service with delay problem. In this problem, there are $n$ points in a metric space that issue service requests over time, and a server that serves these requests. The goal is to minimize the sum of distance traveled by the server and the total delay in serving the requests. This problem models the fundamental tradeoff between batching requests to improve locality and reducing delay to improve response time, that has many applications in operations management, operating systems, logistics, supply chain management, and scheduling. Our main result is to show a poly-logarithmic competitive ratio for the online service with delay problem. This result is obtained by an algorithm that we call the preemptive service algorithm. The salient feature of this algorithm is a process called preemptive service, which uses a novel combination of (recursive) time forwarding and spatial exploration on a metric space. We hope this technique will be useful for related problems such as reordering buffer management, online TSP, vehicle routing, etc. We also generalize our results to $k > 1$ servers. |
| Sesquickselect | Because of unmatched improvements in CPU performance, memory transfers have become a bottleneck of program execution. As discovered in recent years, this also affects sorting in internal memory. Since partitioning around several pivots reduces overall memory transfers, we have seen renewed interest in multiway Quicksort. Here, we analyze in how far multiway partitioning helps in Quickselect. We compute the expected number of comparisons and scanned elements (approximating memory transfers) for a generic class of (non-adaptive) multiway Quickselect and show that three or more pivots are not helpful, but two pivots are. Moreover, we consider ‘adaptive’ variants which choose partitioning and pivot-selection methods in each recursive step from a finite set of alternatives depending on the current (relative) sought rank. We show that ‘Sesquickselect’, a new Quickselect variant that uses either one or two pivots, makes better use of small samples w.r.t. memory transfers than other Quickselect variants. |
| Session-based Recommendation with Graph Neural Network (SR-GNN) |
The problem of session-based recommendation aims to predict users’ actions based on anonymous sessions. Previous methods on the session-based recommendation most model a session as a sequence and capture users’ preference to make recommendations. Though achieved promising results, they fail to consider the complex items transitions among all session sequences, and are insufficient to obtain accurate users’ preference in the session. To better capture the structure of the user-click sessions and take complex transitions of items into account, we propose a novel method, i.e. Session-based Recommendation with Graph Neural Networks, SR-GNN for brevity. In the proposed method, session sequences are aggregated together and modeled as graph-structure data. Based on this graph, GNN can capture complex transitions of items, which are difficult to be revealed by the conventional sequential methods. Each session is then represented as the composition of the global preference and current interests of the session using an attention network. Extensive experiments conducted on two real datasets show that SR-GNN evidently outperforms the state-of-the-art session-based recommendation methods and always obtain stable performance with different connection schemes, session representations, and session lengths. |
| Set Aggregating Network (SAN) |
We construct a general unified framework for learning representation of structured data, i.e. data which cannot be represented as the fixed-length vectors (e.g. sets, graphs, texts or images of varying sizes). The key factor is played by an intermediate network called SAN (Set Aggregating Network), which maps a structured object to a fixed length vector in a high dimensional latent space. Our main theoretical result shows that for sufficiently large dimension of the latent space, SAN is capable of learning a unique representation for every input example. Experiments demonstrate that replacing pooling operation by SAN in convolutional networks leads to better results in classifying images with different sizes. Moreover, its direct application to text and graph data allows to obtain results close to SOTA, by simpler networks with smaller number of parameters than competitive models. |
| Set Cross Entropy | We propose a permutation-invariant loss function designed for the neural networks reconstructing a set of elements without considering the order within its vector representation. Unlike popular approaches for encoding and decoding a set, our work does not rely on a carefully engineered network topology nor by any additional sequential algorithm. The proposed method, Set Cross Entropy, has a natural information-theoretic interpretation and is related to the metrics defined for sets. We evaluate the proposed approach in two object reconstruction tasks and a rule learning task. |
| SetExpander | We present SetExpander, a corpus-based system for expanding a seed set of terms into amore complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to-end workflow. It enables users to easily select a seed set of terms, expand it, view the expanded set, validate it, re-expand the validated set and store it, thus simplifying the extraction of domain-specific fine-grained semantic classes. SetExpander has been used successfully in real-life use cases including integration into an automated recruitment system and an issues and defects resolution system. A video demo of SetExpander is available at https://…open?id=1e545bB87Autsch36DjnJHmq3HWfSd1Rv (some images were blurred for privacy reasons) |
| Seven Pillars of the Causal Revolution | What you can do with a causal model that you could not do without? Pillar 1: Encoding Causal Assumptions – Transparency and Testability Pillar 2: Do-calculus and the control of confounding Pillar 3: The Algorithmization of Counterfactuals Pillar 4: Mediation Analysis and the Assessment of Direct and Indirect Effects Pillar 5: External Validity and Sample Selection Bias Pillar 6: Missing Data Pillar 7: Causal Discovery |
| SFIEGARCH | Here we develop the theory of seasonal FIEGARCH processes, denoted by SFIEGARCH, establishing conditions for the existence, the invertibility, the stationarity and the ergodicity of these processes. We analyze their asymptotic dependence structure by means of the autocovariance and autocorrelation functions. We also present some properties regarding their spectral representation. All properties are illustrated through graphical examples and an application of SFIEGARCH models to describe the volatility of the S&P500 US stock index log-return time series in the period from December 13, 2004 to October 10, 2009 is provided. |
| SGAN | The Generative Adversarial Networks (GANs) have demonstrated impressive performance for data synthesis, and are now used in a wide range of computer vision tasks. In spite of this success, they gained a reputation for being difficult to train, what results in a time-consuming and human-involved development process to use them. We consider an alternative training process, named SGAN, in which several adversarial ‘local’ pairs of networks are trained independently so that a ‘global’ supervising pair of networks can be trained against them. The goal is to train the global pair with the corresponding ensemble opponent for improved performances in terms of mode coverage. This approach aims at increasing the chances that learning will not stop for the global pair, preventing both to be trapped in an unsatisfactory local minimum, or to face oscillations often observed in practice. To guarantee the latter, the global pair never affects the local ones. The rules of SGAN training are thus as follows: the global generator and discriminator are trained using the local discriminators and generators, respectively, whereas the local networks are trained with their fixed local opponent. Experimental results on both toy and real-world problems demonstrate that this approach outperforms standard training in terms of better mitigating mode collapse, stability while converging and that it surprisingly, increases the convergence speed as well. |
| Shakeout | Recent years have witnessed the success of deep neural networks in dealing with a plenty of practical problems. Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training. In this paper, we present a new regularized training approach: Shakeout. Instead of randomly discarding units as Dropout does at the training stage, Shakeout randomly chooses to enhance or reverse each unit’s contribution to the next layer. This minor modification of Dropout has the statistical trait: the regularizer induced by Shakeout adaptively combines $L_0$, $L_1$ and $L_2$ regularization terms. Our classification experiments with representative deep architectures on image datasets MNIST, CIFAR-10 and ImageNet show that Shakeout deals with over-fitting effectively and outperforms Dropout. We empirically demonstrate that Shakeout leads to sparser weights under both unsupervised and supervised settings. Shakeout also leads to the grouping effect of the input units in a layer. Considering the weights in reflecting the importance of connections, Shakeout is superior to Dropout, which is valuable for the deep model compression. Moreover, we demonstrate that Shakeout can effectively reduce the instability of the training process of the deep architecture. |
| Shake-Shake Regularization | The method introduced in this paper aims at helping deep learning practitioners faced with an overfit problem. The idea is to replace, in a multi-branch network, the standard summation of parallel branches with a stochastic affine combination. Applied to 3-branch residual networks, shake-shake regularization improves on the best single shot published results on CIFAR-10 and CIFAR-100 by reaching test errors of 2.86% and 15.85%. Experiments on architectures without skip connections or Batch Normalization show encouraging results and open the door to a large set of applications. Code is available at https://…/shake-shake. Review: Shake-Shake Regularization (Image Classification) |
| Shallow Triple Stream Three-Dimensional CNN (STSTNet) |
In the recent year, the state-of-the-arts of facial micro-expression recognition task have been significantly advanced by the emergence of data-driven approaches based on deep learning. Due to the superb learning capacity of deep learning, it generates promising performance beyond the traditional handcrafted approaches. Recently, many researchers have focused on developing better networks by increasing its depth, as deep networks can effectively approximate certain function classes more efficiently than shallow ones. In this paper, we aim to design a shallow network to extract the high level features of the micro-expression details. Specifically, a two-layer neural network, namely Shallow Triple Stream Three-dimensional CNN (STSTNet) is proposed. The network is capable to learn the features from three optical flow features (i.e., optical strain, horizontal and vertical optical flow images) computed from the onset and apex frames from each video. Our experimental results demonstrate the viability of the proposed STSTNet, which exhibits the UAR recognition results of 76.05%, 70.13%, 86.86% and 68.10% in composite, SMIC, CASME II and SAMM databases, respectively. |
| Shallow-Deep Network (SDN) |
While deep neural networks (DNNs) can perform complex classification tasks, most of their natural inputs do not necessitate the depth of the modern architectures. This leads to wasted computation, as the network overthinks on the simpler inputs. The overthinking problem could be prevented if standard DNNs could produce early predictions. However, prior work suggests that this is challenging in existing architectures, such as ResNet, as their internal layers are not trained for classification and optimizing them for accurate predictions hurts the end performance. In this paper, we explore the overthinking problem, and, as a remedy, we propose a generic modification to off-the-shelf DNNs—the Shallow-Deep Network (SDN). With this modification, a DNN can efficiently produce predictions from either shallow or deep layers, as appropriate for the given input. We employ feature reduction and a layer-wise objective function to train these progressively deeper internal classifiers while preserving the end-performance. We can apply the SDN modification either by training from scratch or by tuning a pre-trained model. Experiments on four architectures (VGG, ResNet, WideResNet, and MobileNet) and three image classifications tasks suggest that, for an average input, an SDN can produce a correct prediction before its middle layer. By avoiding unnecessary computation, the SDN can reduce the required number of operations for an input by 41% over the original network. Finally, we observe that disagreements among the early classifiers reliably indicate inputs where the network is likely to make a mistake. Building on this observation we propose an internal confusion metric and a method to diagnose misclassifications by visualizing these disagreements. |
| Shampoo | Preconditioned gradient methods are among the most general and powerful tools in optimization. However, preconditioning requires storing and manipulating prohibitively large matrices. We describe and analyze a new structure-aware preconditioning algorithm, called Shampoo, for stochastic optimization over tensor spaces. Shampoo maintains a set of preconditioning matrices, each of which operates on a single dimension, contracting over the remaining dimensions. We establish convergence guarantees in the stochastic convex setting, the proof of which builds upon matrix trace inequalities. Our experiments with state-of-the-art deep learning models show that Shampoo is capable of converging considerably faster than commonly used optimizers. Although it involves a more complex update rule, Shampoo’s runtime per step is comparable to that of simple gradient methods such as SGD, AdaGrad, and Adam. |
| SHAnnon DEcay (SHADE) |
Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant representations in the regularizer and the learning of correlations between inputs and labels in the data fitting term. Our second contribution is to derive a stochastic version of the regularizer compatible with deep learning, resulting in a tractable training scheme. We empirically validate the efficiency of our approach to improve classification performances compared to standard regularization schemes on several standard architectures. |
| Shannon-Hartley Theorem | In information theory, the Shannon-Hartley theorem tells the maximum rate at which information can be transmitted over a communications channel of a specified bandwidth in the presence of noise. It is an application of the noisy-channel coding theorem to the archetypal case of a continuous-time analog communications channel subject to Gaussian noise. The theorem establishes Shannon’s channel capacity for such a communication link, a bound on the maximum amount of error-free digital data (that is, information) that can be transmitted with a specified bandwidth in the presence of the noise interference, assuming that the signal power is bounded, and that the Gaussian noise process is characterized by a known power or power spectral density. The law is named after Claude Shannon and Ralph Hartley. |
| ShapeMask | Instance segmentation aims to detect and segment individual objects in a scene. Most existing methods rely on precise mask annotations of every category. However, it is difficult and costly to segment objects in novel categories because a large number of mask annotations is required. We introduce ShapeMask, which learns the intermediate concept of object shape to address the problem of generalization in instance segmentation to novel categories. ShapeMask starts with a bounding box detection and gradually refines it by first estimating the shape of the detected object through a collection of shape priors. Next, ShapeMask refines the coarse shape into an instance level mask by learning instance embeddings. The shape priors provide a strong cue for object-like prediction, and the instance embeddings model the instance specific appearance information. ShapeMask significantly outperforms the state-of-the-art by 6.4 and 3.8 AP when learning across categories, and obtains competitive performance in the fully supervised setting. It is also robust to inaccurate detections, decreased model capacity, and small training data. Moreover, it runs efficiently with 150ms inference time and trains within 11 hours on TPUs. With a larger backbone model, ShapeMask increases the gap with state-of-the-art to 9.4 and 6.2 AP across categories. Code will be released. |
| ShapeSearch | Identifying trendline visualizations with desired patterns is a common and fundamental data exploration task. Existing visual analytics tools offer limited flexibility and expressiveness for such tasks, especially when the pattern of interest is under-specified and approximate, and do not scale well when the pattern searching needs are ad-hoc, as is often the case. We propose ShapeSearch, an efficient and flexible pattern-searching tool, that enables the search for desired patterns via multiple mechanisms: sketch, natural-language, and visual regular expressions. We develop a novel shape querying algebra, with a minimal set of primitives and operators that can express a large number of ShapeSearch queries, and design a natural-language and regex-based parser to automatically parse and translate user queries to the algebra representation. To execute these queries within interactive response times, ShapeSearch uses a fast shape algebra-based execution engine with query-aware optimizations, and perceptually-aware scoring methodologies. We present a thorough evaluation of the system, including a general-purpose user study, a case study involving genomic data analysis, as well as performance experiments, comparing against state-of-the-art time series shape matching approaches—that together demonstrate the usability and scalability of ShapeSearch. |
| SHapley Additive exPlanation (SHAP) |
Understanding why a model makes a certain prediction can be as crucial as the prediction’s accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle to interpret, such as ensemble or deep learning models, creating a tension between accuracy and interpretability. In response, various methods have recently been proposed to help users interpret the predictions of complex models, but it is often unclear how these methods are related and when one method is preferable over another. To address this problem, we present a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations). SHAP assigns each feature an importance value for a particular prediction. Its novel components include: (1) the identification of a new class of additive feature importance measures, and (2) theoretical results showing there is a unique solution in this class with a set of desirable properties. The new class unifies six existing methods, notable because several recent methods in the class lack the proposed desirable properties. Based on insights from this unification, we present new methods that show improved computational performance and/or better consistency with human intuition than previous approaches. Demystifying Black-Box Models with SHAP Value Analysis |
| Shapley Regression Framework | Machine learning models often excel in the accuracy of their predictions but are opaque due to their non-linear and non-parametric structure. This makes statistical inference challenging and disqualifies them from many applications where model interpretability is crucial. This paper proposes the Shapley regression framework as an approach for statistical inference on non-linear or non-parametric models. Inference is performed based on the Shapley value decomposition of a model, a pay-off concept from cooperative game theory. I show that universal approximators from machine learning are estimation consistent and introduce hypothesis tests for individual variable contributions, model bias and parametric functional forms. The inference properties of state-of-the-art machine learning models – like artificial neural networks, support vector machines and random forests – are investigated using numerical simulations and real-world data. The proposed framework is unique in the sense that it is identical to the conventional case of statistical inference on a linear model if the model is linear in parameters. This makes it a well-motivated extension to more general models and strengthens the case for the use of machine learning to inform decisions. |
| Shapley-Taylor Interaction Index | We study interactions among players in cooperative games. We propose a new interaction index called Shapley-Taylor interaction index. It decomposes the value of the game into terms that model the interactions between subsets of players, analogous to how the Taylor series represents a function in terms of its derivatives of various orders. We axiomatize the method using the standard Shapley axioms–linearity, dummy, symmetry and efficiency–and also an additional axiom that we call the interaction distribution axiom. This new axiom explicitly characterizes how inter-actions are distributed for a class of games called interaction games. We contrast the Shapley-Taylor interaction index against the previously pro-posed Shapley Interaction index and the Banzhaf interaction index (cf. [2]). |
| Sharding | Sharding is the process of splitting up your data so it resides in different tables or often different physical databases. Sharding is helpful when you have some specific set of data that outgrows either storage or reasonable performance within a single database. SHapley Additive exPlanations – SHAP |
| Shared Learning Framework | Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward. However, most of these successes rely on algorithms that require a large amount of data to train in order to obtain results on par with human-level performance. This is not feasible if we are to deploy these systems on real world tasks and hence there has been an increased thrust in exploring data efficient algorithms. To this end, we propose the Shared Learning framework aimed at making $Q$-ensemble algorithms data-efficient. For achieving this, we look into some principles of transfer learning which aim to study the benefits of information exchange across tasks in reinforcement learning and adapt transfer to learning our value function estimates in a novel manner. In this paper, we consider the special case of transfer between the value function estimates in the $Q$-ensemble architecture of BootstrappedDQN. We further empirically demonstrate how our proposed framework can help in speeding up the learning process in $Q$-ensembles with minimum computational overhead on a suite of Atari 2600 Games. |
| ShareLaTeX | An easy to use, online, collaborative LaTeX editor. |
| Shark | SHARK is a fast, modular, feature-rich open-source C++ machine learning library. It provides methods for linear and nonlinear optimization, kernel-based learning algorithms, neural networks, and various other machine learning techniques (see the feature list below). It serves as a powerful toolbox for real world applications as well as research. Shark depends on Boost and CMake. It is compatible with Windows, Solaris, MacOS X, and Linux. Shark is licensed under the permissive GNU Lesser General Public License. RcppShark |
| Shark | Shark is an open source distributed SQL query engine for Hadoop data. It brings state-of-the-art performance and advanced analytics to Hive users. By running on Spark, Shark can call complex analytics functions like machine learning right from SQL. Or call Shark inside your Spark jobs to load Hive data. |
| Sharma-Mittal Entropy of a Graph | In this article, we introduce the Sharma-Mittal entropy of a graph, which is a generalization of the existing idea of the von-Neumann entropy. The well-known R{\’e}nyi, Thallis, and von-Neumann entropies can be expressed as limiting cases of Sharma-Mittal entropy. We have explicitly calculated them for cycle, path, and complete graphs. Also, we have proposed a number of bounds for these entropies. In addition, we have also discussed the entropy of product graphs, such as Cartesian, Kronecker, Lexicographic, Strong, and Corona products. The change in entropy can also be utilized in the analysis of growing network models (Corona graphs), useful in generating complex networks. |
| Sharp Differentiable Architecture Search (sharpDARTS) |
Neural Architecture Search (NAS) has been a source of dramatic improvements in neural network design, with recent results meeting or exceeding the performance of hand-tuned architectures. However, our understanding of how to represent the search space for neural net architectures and how to search that space efficiently are both still in their infancy. We have performed an in-depth analysis to identify limitations in a widely used search space and a recent architecture search method, Differentiable Architecture Search (DARTS). These findings led us to introduce novel network blocks with a more general, balanced, and consistent design; a better-optimized Cosine Power Annealing learning rate schedule; and other improvements. Our resulting sharpDARTS (sharp Differentiable Architecture Search) search is 50% faster with a 20-30% relative improvement in final model error on CIFAR-10 when compared to DARTS. Our best single model run has 1.93% (1.98+/-0.07) validation error on CIFAR-10 and 5.5% error (5.8+/-0.3) on the recently released CIFAR-10.1 test set. To our knowledge, both are state of the art for models of similar size. This model also generalizes competitively to ImageNet at 25.1% top-1 (7.8% top-5) error. We found improvements for existing search spaces but does DARTS generalize to new domains? We propose Differentiable Hyperparameter Grid Search and the HyperCuboid search space, which are representations designed to leverage DARTS for more general parameter optimization. Here we find that DARTS fails to generalize when compared against a human’s one shot choice of models. We look back to the DARTS and sharpDARTS search spaces to understand why, and an ablation study reveals an unusual generalization gap. We finally propose Max-W regularization to solve this problem, which proves significantly better than the handmade design. Code will be made available. |
| Sharpness | It is well-known that, without restricting treatment effect heterogeneity, instrumental variable (IV) methods only identify ‘local’ effects among compliers, i.e., those subjects who take treatment only when encouraged by the IV. Local effects are controversial since they seem to only apply to an unidentified subgroup; this has led many to denounce these effects as having little policy relevance. However, we show that such pessimism is not always warranted: it is possible in some cases to accurately predict who compliers are, and obtain tight bounds on more generalizable effects in identifiable subgroups. We propose methods for doing so and study their estimation error and asymptotic properties, showing that these tasks can in theory be accomplished even with very weak IVs. We go on to introduce a new measure of IV quality called ‘sharpness’, which reflects the variation in compliance explained by covariates, and captures how well one can identify compliers and obtain tight bounds on identifiable subgroup effects. We develop an estimator of sharpness, and show that it is asymptotically efficient under weak conditions. Finally we explore finite-sample properties via simulation, and apply the methods to study canvassing effects on voter turnout. We propose that sharpness should be presented alongside strength to assess IV quality. |
| Sheffield Elicitation Framework (SHELF) |
The SHeffield ELicitation Framework (SHELF) is a package of documents, templates and software to carry out elicitation of probability distributions for uncertain quantities from a group of experts. Elicitation is increasingly important for quantifying expert knowledge in situations where hard data are sparse. This is often the context in which difficult policy decisions are made. It is generally important to elicit from a group of experts, rather than a single expert, in order to synthesise the range of knowledge and opinions of the expert community. (However, SHELF may be used for a single expert with only trivial modification.) SHELF |
| ShelfNet | In this project, we present ShelfNet, a lightweight convolutional neural network for accurate real-time semantic segmentation. Different from the standard encoder-decoder structure, ShelfNet has multiple encoder-decoder branch pairs with skip connections at each spatial level, which looks like a shelf with multiple columns. The shelf-shaped structure provides multiple paths for information flow and improves segmentation accuracy. Inspired by the success of recurrent convolutional neural networks, we use modified residual blocks where two convolutional layers share weights. The shared-weight block enables efficient feature extraction and model size reduction. We tested ShelfNet with ResNet50 and ResNet101 as the backbone respectively: they achieved 59 FPS and 42 FPS respectively on a GTX 1080Ti GPU with a 512×512 input image. ShelfNet achieved high accuracy: on PASCAL VOC 2012 test set, it achieved 84.2% mIoU with ResNet101 backbone and 82.8% mIoU with ResNet50 backbone; it achieved 75.8% mIoU with ResNet50 backbone on Cityscapes dataset. ShelfNet achieved both higher mIoU and faster inference speed compared with state-of-the-art real-time semantic segmentation models. We provide the implementation https://…/ShelfNet. |
| Shelling | In mathematics, a shelling of a simplicial complex is a way of gluing it together from its maximal simplices (simplices that are not a face of another simplex) in a well-behaved way. A complex admitting a shelling is called shellable. Counting Shellings of Complete Bipartite Graphs and Trees |
| Shewhart Control Chart | Control charts, also known as Shewhart charts (after Walter A. Shewhart) or process-behavior charts, are a statistical process control tool used to determine if a manufacturing or business process is in a state of control. If analysis of the control chart indicates that the process is currently under control (i.e., is stable, with variation only coming from sources common to the process), then no corrections or changes to process control parameters are needed or desired. In addition, data from the process can be used to predict the future performance of the process. If the chart indicates that the monitored process is not in control, analysis of the chart can help determine the sources of variation, as this will result in degraded process performance. A process that is stable but operating outside desired (specification) limits (e.g., scrap rates may be in statistical control but above desired limits) needs to be improved through a deliberate effort to understand the causes of current performance and fundamentally improve the process. The control chart is one of the seven basic tools of quality control. Typically control charts are used for time-series data, though they can be used for data that have logical comparability (i.e. you want to compare samples that were taken all at the same time, or the performance of different individuals); however the type of chart used to do this requires consideration. |
| Shift Compensation Network (SCN) |
Citizen science projects are successful at gathering rich datasets for various applications. Nevertheless, the data collected by the citizen scientists are often biased, more aligned with the citizens’ preferences rather than scientific objectives. We propose the Shift Compensation Network (SCN), an end-to-end learning scheme which learns the shift from the scientific objectives to the biased data, while compensating the shift by re-weighting the training data. Applied to bird observational data from the citizen science project \textit{eBird}, we demonstrate how SCN quantifies the data distribution shift as well as outperforms supervised learning models that do not address the data bias. Compared with other competing models in the context of covariate shift, we further demonstrate the advantage of SCN in both the effectiveness and the capability of handling massive high-dimensional data. |
| ShiftCNN | In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs). ShiftCNN is based on a power-of-two weight representation and, as a result, performs only shift and addition operations. Furthermore, ShiftCNN substantially reduces computational cost of convolutional layers by precomputing convolution terms. Such an optimization can be applied to any CNN architecture with a relatively small codebook of weights and allows to decrease the number of product operations by at least two orders of magnitude. The proposed architecture targets custom inference accelerators and can be realized on FPGAs or ASICs. Extensive evaluation on ImageNet shows that the state-of-the-art CNNs can be converted without retraining into ShiftCNN with less than 1% drop in accuracy when the proposed quantization algorithm is employed. RTL simulations, targeting modern FPGAs, show that power consumption of convolutional layers is reduced by a factor of 4 compared to conventional 8-bit fixed-point architectures. |
| Shiryaev’s Bayesian Quickest Change Detection (QCD) |
This paper provides the first description of a weak practical super-martingale phenomenon that can emerge in the test statistic in Shiryaev’s Bayesian quickest change detection (QCD) problem. We establish that this super-martingale phenomenon can emerge under a condition on the relative entropy between pre and post change densities when the measurements are insufficiently informative to overcome the change time’s geometric prior. We illustrate this super-martingale phenomenon in a simple Bayesian QCD problem which highlights the unsuitability of Shiryaev’s test statistic for detecting subtle change events. |
| Shogun | Shogun is and open-source machine learning library that offers a wide range of efficient and unified machine learning methods. |
| SHOPPER | We develop SHOPPER, a sequential probabilistic model of market baskets. SHOPPER uses interpretable components to model the forces that drive how a customer chooses products; in particular, we designed SHOPPER to capture how items interact with other items. We develop an efficient posterior inference algorithm to estimate these forces from large-scale data, and we analyze a large dataset from a major chain grocery store. We are interested in answering counterfactual queries about changes in prices. We found that SHOPPER provides accurate predictions even under price interventions, and that it helps identify complementary and substitutable pairs of products. |
| Short Term Attentive Working Memory Model (STAWM) |
The ability to look multiple times through a series of pose-adjusted glimpses is fundamental to human vision. This critical faculty allows us to understand highly complex visual scenes. Short term memory plays an integral role in aggregating the information obtained from these glimpses and informing our interpretation of the scene. Computational models have attempted to address glimpsing and visual attention but have failed to incorporate the notion of memory. We introduce a novel, biologically inspired visual working memory architecture that we term the Hebb-Rosenblatt memory. We subsequently introduce a fully differentiable Short Term Attentive Working Memory model (STAWM) which uses transformational attention to learn a memory over each image it sees. The state of our Hebb-Rosenblatt memory is embedded in STAWM as the weights space of a layer. By projecting different queries through this layer we can obtain goal-oriented latent representations for tasks including classification and visual reconstruction. Our model obtains highly competitive classification performance on MNIST and CIFAR-10. As demonstrated through the CelebA dataset, to perform reconstruction the model learns to make a sequence of updates to a canvas which constitute a parts-based representation. Classification with the self supervised representation obtained from MNIST is shown to be in line with the state of the art models (none of which use a visual attention mechanism). Finally, we show that STAWM can be trained under the dual constraints of classification and reconstruction to provide an interpretable visual sketchpad which helps open the ‘black-box’ of deep learning. |
| Short Text Classification With Knowledge Powered Attention (STCKA) |
Short text classification is one of important tasks in Natural Language Processing (NLP). Unlike paragraphs or documents, short texts are more ambiguous since they have not enough contextual information, which poses a great challenge for classification. In this paper, we retrieve knowledge from external knowledge source to enhance the semantic representation of short texts. We take conceptual information as a kind of knowledge and incorporate it into deep neural networks. For the purpose of measuring the importance of knowledge, we introduce attention mechanisms and propose deep Short Text Classification with Knowledge powered Attention (STCKA). We utilize Concept towards Short Text (C- ST) attention and Concept towards Concept Set (C-CS) attention to acquire the weight of concepts from two aspects. And we classify a short text with the help of conceptual information. Unlike traditional approaches, our model acts like a human being who has intrinsic ability to make decisions based on observation (i.e., training data for machines) and pays more attention to important knowledge. We also conduct extensive experiments on four public datasets for different tasks. The experimental results and case studies show that our model outperforms the state-of-the-art methods, justifying the effectiveness of knowledge powered attention. |
| Short Text Topic Modeling (STTM) |
Analyzing short texts infers discriminative and coherent latent topics that is a critical and fundamental task since many real-world applications require semantic understanding of short texts. Traditional long text topic modeling algorithms (e.g., PLSA and LDA) based on word co-occurrences cannot solve this problem very well since only very limited word co-occurrence information is available in short texts. Therefore, short text topic modeling has already attracted much attention from the machine learning research community in recent years, which aims at overcoming the problem of sparseness in short texts. In this survey, we conduct a comprehensive review of various short text topic modeling techniques proposed in the literature. We present three categories of methods based on Dirichlet multinomial mixture, global word co-occurrences, and self-aggregation, with example of representative approaches in each category and analysis of their performance on various tasks. We develop the first comprehensive open-source library, called STTM, for use in Java that integrates all surveyed algorithms within a unified interface, benchmark datasets, to facilitate the expansion of new methods in this research field. Finally, we evaluate these state-of-the-art methods on many real-world datasets and compare their performance against one another and versus long text topic modeling algorithm. |
| Shortest Dependency Path – Long Short Term Memory (SDP-LSTM) |
Relation classification is an important research arena in the field of natural language processing (NLP). In this paper, we present SDP-LSTM, a novel neural network to classify the relation of two entities in a sentence. Our neural architecture leverages the shortest dependency path (SDP) between two entities; multichannel recurrent neural networks, with long short term memory (LSTM) units, pick up heterogeneous information along the SDP. Our proposed model has several distinct features: (1) The shortest dependency paths retain most relevant information (to relation classification), while eliminating irrelevant words in the sentence. (2) The multichannel LSTM networks allow effective information integration from heterogeneous sources over the dependency paths. (3) A customized dropout strategy regularizes the neural network to alleviate overfitting. We test our model on the SemEval 2010 relation classification task, and achieve an $F_1$-score of 83.7\%, higher than competing methods in the literature. |
| Shortest Path Faster Algorithm (SPFA) |
The Shortest Path Faster Algorithm (SPFA) is an improvement of the Bellman-Ford algorithm which computes single-source shortest paths in a weighted directed graph. The algorithm is believed to work well on random sparse graphs and is particularly suitable for graphs that contain negative-weight edges. However, the worst-case complexity of SPFA is the same as that of Bellman-Ford, so for graphs with nonnegative edge weights Dijkstra’s algorithm is preferred. The SPFA algorithm was published in 1994 by Fanding Duan. |
| Shortest Probability Interval (SPIn) |
SPIn |
| Shortest Processing Time (SPT) |
The shortest processing time rule orders the jobs in the order of increasing processing times. Whenever a machine is freed, the shortest job ready at the time will begin processing. This algorithm is optimal for finding the minimum total completion time and weighted completion time. In the single machine environment with ready time at 0 for all jobs, this algorithm is optimal in minimizing the mean flow time, minimizing the mean number of jobs in the system, minimizing the mean waiting time of the jobs from the time of arrival to the start of processing, minimizing the maximum waiting time and the mean lateness. |
| Short-Term Cognitive Network | While the machine learning literature dedicated to fully automated reasoning algorithms is abundant, the number of methods enabling the inference process on the basis of previously defined knowledge structures is scanter. Fuzzy Cognitive Maps (FCMs) are neural networks that can be exploited towards this goal because of their flexibility to handle external knowledge. However, FCMs suffer from a number of issues that range from the limited prediction horizon to the absence of theoretically sound learning algorithms able to produce accurate predictions. In this paper, we propose a neural network system named Short-term Cognitive Networks that tackle some of these limitations. In our model weights are not constricted and may have a causal nature or not. As a second contribution, we present a nonsynaptic learning algorithm to improve the network performance without modifying the previously defined weights. Moreover, we derive a stop condition to prevent the learning algorithm from iterating without decreasing the simulation error. |
| Short-Time Fourier Neural Network (STFNet) |
Recent advances in deep learning motivate the use of deep neural networks in Internet-of-Things (IoT) applications. These networks are modelled after signal processing in the human brain, thereby leading to significant advantages at perceptual tasks such as vision and speech recognition. IoT applications, however, often measure physical phenomena, where the underlying physics (such as inertia, wireless signal propagation, or the natural frequency of oscillation) are fundamentally a function of signal frequencies, offering better features in the frequency domain. This observation leads to a fundamental question: For IoT applications, can one develop a new brand of neural network structures that synthesize features inspired not only by the biology of human perception but also by the fundamental nature of physics? Hence, in this paper, instead of using conventional building blocks (e.g., convolutional and recurrent layers), we propose a new foundational neural network building block, the Short-Time Fourier Neural Network (STFNet). It integrates a widely-used time-frequency analysis method, the Short-Time Fourier Transform, into data processing to learn features directly in the frequency domain, where the physics of underlying phenomena leave better foot-prints. STFNets bring additional flexibility to time-frequency analysis by offering novel nonlinear learnable operations that are spectral-compatible. Moreover, STFNets show that transforming signals to a domain that is more connected to the underlying physics greatly simplifies the learning process. We demonstrate the effectiveness of STFNets with extensive experiments. STFNets significantly outperform the state-of-the-art deep learning models in all experiments. A STFNet, therefore, demonstrates superior capability as the fundamental building block of deep neural networks for IoT applications for various sensor inputs. |
| Short-Time Fourier Transform (STFT) |
Recently, we proposed short-time Fourier transform (STFT)-based loss functions for training a neural speech waveform model. In this paper, we generalize the above framework and propose a training scheme for such models based on spectral amplitude and phase losses obtained by either STFT or continuous wavelet transform (CWT), or both of them. Since CWT is capable of having time and frequency resolutions different from those of STFT and is cable of considering those closer to human auditory scales, the proposed loss functions could provide complementary information on speech signals. Experimental results showed that it is possible to train a high-quality model by using the proposed CWT spectral loss and is as good as one using STFT-based loss. |
| ShotgunWSD | In this paper, we present a novel unsupervised algorithm for word sense disambiguation (WSD) at the document level. Our algorithm is inspired by a widely-used approach in the field of genetics for whole genome sequencing, known as the Shotgun sequencing technique. The proposed WSD algorithm is based on three main steps. First, a brute-force WSD algorithm is applied to short context windows (up to 10 words) selected from the document in order to generate a short list of likely sense configurations for each window. In the second step, these local sense configurations are assembled into longer composite configurations based on suffix and prefix matching. The resulted configurations are ranked by their length, and the sense of each word is chosen based on a voting scheme that considers only the top k configurations in which the word appears. We compare our algorithm with other state-of-the-art unsupervised WSD algorithms and demonstrate better performance, sometimes by a very large margin. We also show that our algorithm can yield better performance than the Most Common Sense (MCS) baseline on one data set. Moreover, our algorithm has a very small number of parameters, is robust to parameter tuning, and, unlike other bio-inspired methods, it gives a deterministic solution (it does not involve random choices). |
| Shrinkage | In statistics, shrinkage has two meanings: · In relation to the general observation that, in regression analysis, a fitted relationship appears to perform less well on a new data set than on the data set used for fitting. In particular the value of the coefficient of determination ‘shrinks’. This idea is complementary to overfitting and, separately, to the standard adjustment made in the coefficient of determination to compensate for the subjunctive effects of further sampling, like controlling for the potential of new explanatory terms improving the model by chance: that is, the adjustment formula itself provides ‘shrinkage.’ But the adjustment formula yields an artificial shrinkage, in contrast to the first definition. · To describe general types of estimators, or the effects of some types of estimation, whereby a naive or raw estimate is improved by combining it with other information (➘ “Shrinkage Estimator”). The term relates to the notion that the improved estimate is at a reduced distance from the value supplied by the ‘other information’ than is the raw estimate. In this sense, shrinkage is used to regularize ill-posed inference problems. A common idea underlying both of these meanings is the reduction in the effects of sampling variation. |
| Shrinkage Estimator | In statistics, a shrinkage estimator is an estimator that, either explicitly or implicitly, incorporates the effects of shrinkage. In loose terms this means that a naive or raw estimate is improved by combining it with other information. The term relates to the notion that the improved estimate is made closer to the value supplied by the ‘other information’ than the raw estimate. In this sense, shrinkage is used to regularize ill-posed inference problems. |
| Shrinkwrap | A private data federation is a set of autonomous databases that share a unified query interface offering in-situ evaluation of SQL queries over the union of the sensitive data of its members. Owing to privacy concerns, these systems do not have a trusted data collector that can see all their data and their member databases cannot learn about individual records of other engines. Federations currently achieve this goal by evaluating queries obliviously using secure multiparty computation. This hides the intermediate result cardinality of each query operator by exhaustively padding it. With cascades of such operators, this padding accumulates to a blow-up in the output size of each operator and a proportional loss in query performance. Hence, existing private data federations do not scale well to complex SQL queries over large datasets. We introduce Shrinkwrap, a private data federation that offers data owners a differentially private view of the data held by others to improve their performance over oblivious query processing. Shrinkwrap uses computational differential privacy to minimize the padding of intermediate query results, achieving up to 35X performance improvement over oblivious query processing. When the query needs differentially private output, Shrinkwrap provides a trade-off between result accuracy and query evaluation performance. |
| Shrunken Centroids Regularized Discriminant Analysis (SCRDA) |
In this paper, we introduce a modified version of linear discriminant analysis, called ‘shrunken centroids regularized discriminant analysis’ (SCRDA). This method generalizes the idea of ‘nearest shrunken centroids’ (NSC) into the classical discriminant analysis. The SCRDA method is specially designed for classification problems in high dimension low sample size situations, for example, microarray data. Through both simulated data and real life data, it is shown that this method performs very well in multivariate classification problems, often outperforms the PAM method and can be as competitive as the SVM classifiers. It is also suitable for feature elimination purpose and can be used as gene selection method. The open source R package for SCRDA is available and will be added to the R libraries in the near future. |
| Shuffled Graph | Shuffled Graphs are graphs with latent vertex labels. |
| ShuffleNASNet | Neural network architectures found by sophistic search algorithms achieve strikingly good test performance, surpassing most human-crafted network models by significant margins. Although computationally efficient, their design is often very complex, impairing execution speed. Additionally, finding models outside of the search space is not possible by design. While our space is still limited, we implement undiscoverable expert knowledge into the economic search algorithm Efficient Neural Architecture Search (ENAS), guided by the design principles and architecture of ShuffleNet V2. While maintaining baseline-like 2.85% test error on CIFAR-10, our ShuffleNASNets are significantly less complex, require fewer parameters, and are two times faster than the ENAS baseline in a classification task. These models also scale well to a low parameter space, achieving less than 5% test error with little regularization and only 236K parameters. |
| ShuffleNet | We introduce an extremely computation efficient CNN architecture named ShuffleNet, designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two proposed operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 6.7\%) than the recent MobileNet system on ImageNet classification under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves \textasciitilde 13$\times$ actual speedup over AlexNet while maintaining comparable accuracy. |
| ShuffleNet V2 | Currently, the neural network architecture design is mostly guided by the \emph{indirect} metric of computation complexity, i.e., FLOPs. However, the \emph{direct} metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical \emph{guidelines} for efficient network design. Accordingly, a new architecture is presented, called \emph{ShuffleNet V2}. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff. |
| shuttleNet | Despite a lot of research efforts devoted in recent years, how to efficiently learn long-term dependencies from sequences still remains a pretty challenging task. As one of the key models for sequence learning, recurrent neural network (RNN) and its variants such as long short term memory (LSTM) and gated recurrent unit (GRU) are still not powerful enough in practice. One possible reason is that they have only feedforward connections, which is different from biological neural network that is typically composed of both feedforward and feedback connections. To address the problem, this paper proposes a biologically-inspired RNN structure, called shuttleNet, by introducing loop connections in the network and utilizing parameter sharing to prevent overfitting. Unlike the traditional RNNs, the cells of shuttleNet are loop connected to mimic the brain’s feedforward and feedback connections. The structure is then stretched in the depth dimension to generate a deeper model with multiple information flow paths, while the parameters are shared so as to prevent shuttleNet from being over-fitting. The attention mechanism is then applied to select the best information path. The extensive experiments are conducted on two datasets for action recognition: UCF101 and HMDB51. We find that our model can outperform LSTMs and GRUs remarkably. Even only replacing the LSTMs with our shuttleNet in a CNN-RNN network, we can still achieve the state-of-the-art performance on both datasets. |
| Siamese Capsule Network | Capsule Networks have shown encouraging results on \textit{defacto} benchmark computer vision datasets such as MNIST, CIFAR and smallNORB. Although, they are yet to be tested on tasks where (1) the entities detected inherently have more complex internal representations and (2) there are very few instances per class to learn from and (3) where point-wise classification is not suitable. Hence, this paper carries out experiments on face verification in both controlled and uncontrolled settings that together address these points. In doing so we introduce \textit{Siamese Capsule Networks}, a new variant that can be used for pairwise learning tasks. The model is trained using contrastive loss with $\ell_2$-normalized capsule encoded pose features. We find that \textit{Siamese Capsule Networks} perform well against strong baselines on both pairwise learning datasets, yielding best results in the few-shot learning setting where image pairs in the test set contain unseen subjects. |
| Siamese Deep Forest (SDF) |
A Siamese Deep Forest (SDF) is proposed in the paper. It is based on the Deep Forest or gcForest proposed by Zhou and Feng and can be viewed as a gcForest modification. It can be also regarded as an alternative to the well-known Siamese neural networks. The SDF uses a modified training set consisting of concatenated pairs of vectors. Moreover, it defines the class distributions in the deep forest as the weighted sum of the tree class probabilities such that the weights are determined in order to reduce distances between similar pairs and to increase them between dissimilar points. We show that the weights can be obtained by solving a quadratic optimization problem. The SDF aims to prevent overfitting which takes place in neural networks when only limited training data are available. The numerical experiments illustrate the proposed distance metric method. |
| Siamese Deep Neural Network | Siamese neural network is a class of neural network architectures that contain two or more identical subnetworks. identical here means they have the same configuration with the same parameters and weights. Parameter updating is mirrored across both subnetworks. Siamese NNs are popular among tasks that involve finding similarity or a relationship between two comparable things. Some examples are paraphrase scoring, where the inputs are two sentences and the output is a score of how similar they are; or signature verification, where figure out whether two signatures are from the same person. Generally, in such tasks, two identical subnetworks are used to process the two inputs, and another module will take their outputs and produce the final output. The picture below is from Bromley et al (1993). They proposed a Siamese architecture for the signature verification task. |
| Siamese Edge-Enhancement Network (SE2Net) |
Deep convolutional neural network significantly boosted the capability of salient object detection in handling large variations of scenes and object appearances. However, convolution operations seek to generate strong responses on individual pixels, while lack the ability to maintain the spatial structure of objects. Moreover, the down-sampling operations, such as pooling and striding, lose spatial details of the salient objects. In this paper, we propose a simple yet effective Siamese Edge-Enhancement Network (SE2Net) to preserve the edge structure for salient object detection. Specifically, a novel multi-stage siamese network is built to aggregate the low-level and high-level features, and parallelly estimate the salient maps of edges and regions. As a result, the predicted regions become more accurate by enhancing the responses at edges, and the predicted edges become more semantic by suppressing the false positives in background. After the refined salient maps of edges and regions are produced by the SE2Net, an edge-guided inference algorithm is designed to further improve the resulting salient masks along the predicted edges. Extensive experiments on several benchmark datasets have been conducted, which show that our method is superior than the state-of-the-art approaches. |
| Siamese Survival Prognosis Network (SSPN) |
Survival analysis in the presence of multiple possible adverse events, i.e., competing risks, is a pervasive problem in many industries (healthcare, finance, etc.). Since only one event is typically observed, the incidence of an event of interest is often obscured by other related competing events. This nonidentifiability, or inability to estimate true cause-specific survival curves from empirical data, further complicates competing risk survival analysis. We introduce Siamese Survival Prognosis Network (SSPN), a novel deep learning architecture for estimating personalized risk scores in the presence of competing risks. SSPN circumvents the nonidentifiability problem by avoiding the estimation of cause-specific survival curves and instead determines pairwise concordant time-dependent risks, where longer event times are assigned lower risks. Furthermore, SSPN is able to directly optimize an approximation to the C-discrimination index, rather than relying on well-known metrics which are unable to capture the unique requirements of survival analysis with competing risks. |
| Sibyl | A system for large scale supervised machine learning. Sibyl is an important research project underway at Google that implements machine learning primitives at scale and is widely used within Google. Large scale machine learning is playing an increasingly important role in improving the quality and monetization of Internet properties. A small number of techniques, such as regression, have proven to be widely applicable across Internet properties and applications. |
| SIF | Solidity is an object-oriented and high-level language for writing smart contracts which are used to execute, verify and enforce credible transactions on permissionless blockchains. In the last few years, analysis of vulnerabilities in smart contracts has raised considerable interest and numerous techniques have been proposed. Current techniques lack traceability in source code and have widely differing work flows. There is no single unifying framework for analysis, instrumentation, optimisation and code generation of Solidity contracts. In this paper, we present SIF, a comprehensive framework for Solidity contract monitoring, instrumenting, and code generation. SIF provides support for Solidity contract developers and testers to build source level techniques for analysis, bug detection, coverage measurement, optimisations and code generation. We show feasibility and applicability of the framework using 51 real smart contracts deployed on the Ethereum network. |
| Sifaka | Text mining and analytics software has become popular, but little attention has been paid to the software architectures of such systems. Often they are built from scratch using special-purpose software and data structures, which increases their cost and complexity. This demo paper describes Sifaka, a new open-source text mining application constructed above a standard search engine index using existing application programmer interface (API) calls. Indexing integrates popular annotation software libraries to augment the full-text index with noun phrase and named-entities; n-grams are also provided. Sifaka enables a person to quickly explore and analyze large text collections using search, frequency analysis, and co-occurrence analysis; and import existing document labels or interactively construct document sets that are positive or negative examples of new concepts, perform feature selection, and export feature vectors compatible with popular machine learning software. Sifaka demonstrates that search engines are good platforms for text mining applications while also making common IR text mining capabilities accessible to researchers in disciplines where programming skills are less common. |
| sigma.js | Sigma is a JavaScript library dedicated to graph drawing. It makes easy to publish networks on Web pages, and allows developers to integrate network exploration in rich Web applications. |
| Sigma-Connection Graphs (sigma-CG) |
➚ “Causal Modeling Framework of Modular Structural Causal Models” |
| Sigma-Delta Networks | Deep neural networks can be obscenely wasteful. When processing video, a convolutional network expends a fixed amount of computation for each frame with no regard to the similarity between neighbouring frames. As a result, it ends up repeatedly doing very similar computations. To put an end to such waste, we introduce Sigma-Delta networks. With each new input, each layer in this network sends a discretized form of its change in activation to the next layer. Thus the amount of computation that the network does scales with the amount of change in the input and layer activations, rather than the size of the network. We introduce an optimization method for converting any pre-trained deep network into an optimally efficient Sigma-Delta network, and show that our algorithm, if run on the appropriate hardware, could cut at least an order of magnitude from the computational cost of processing video data. |
| Sigmoid Function | A sigmoid function is a mathematical function having an “S” shape (sigmoid curve). Often, sigmoid function refers to the special case of the logistic function. |
| Signal Temporal Logic (STL) |
We present a framework to synthesize control policies for nonlinear dynamical systems from complex temporal constraints specified in a rich temporal logic called Signal Temporal Logic (STL). We propose a novel smooth and differentiable STL quantitative semantics called cumulative robustness, and efficiently compute control policies through a series of smooth optimization problems that are solved using gradient ascent algorithms. Furthermore, we demonstrate how these techniques can be incorporated in a model predictive control framework in order to synthesize control policies over long time horizons. The advantages of combining the cumulative robustness function with smooth optimization methods as well as model predictive control are illustrated in case studies. |
| SignalR | ASP.NET SignalR is a new library for ASP.NET developers that makes it incredibly simple to add real-time web functionality to your applications. What is “real-time web” functionality? It’s the ability to have your server-side code push content to the connected clients as it happens, in real-time. You may have heard of WebSockets, a new HTML5 API that enables bi-directional communication between the browser and server. SignalR will use WebSockets under the covers when it’s available, and gracefully fallback to other techniques and technologies when it isn’t, while your application code stays the same. SignalR also provides a very simple, high-level API for doing server to client RPC (call JavaScript functions in your clients’ browsers from server-side .NET code) in your ASP.NET application, as well as adding useful hooks for connection management, e.g. connect/disconnect events, grouping connections, authorization. |
| Signal-to-Noise Ratio (SNR) |
Deep metric learning, which learns discriminative features to process image clustering and retrieval tasks, has attracted extensive attention in recent years. A number of deep metric learning methods, which ensure that similar examples are mapped close to each other and dissimilar examples are mapped farther apart, have been proposed to construct effective structures for loss functions and have shown promising results. In this paper, different from the approaches on learning the loss structures, we propose a robust SNR distance metric based on Signal-to-Noise Ratio (SNR) for measuring the similarity of image pairs for deep metric learning. By exploring the properties of our SNR distance metric from the view of geometry space and statistical theory, we analyze the properties of our metric and show that it can preserve the semantic similarity between image pairs, which well justify its suitability for deep metric learning. Compared with Euclidean distance metric, our SNR distance metric can further jointly reduce the intra-class distances and enlarge the inter-class distances for learned features. Leveraging our SNR distance metric, we propose Deep SNR-based Metric Learning (DSML) to generate discriminative feature embeddings. By extensive experiments on three widely adopted benchmarks, including CARS196, CUB200-2011 and CIFAR10, our DSML has shown its superiority over other state-of-the-art methods. Additionally, we extend our SNR distance metric to deep hashing learning, and conduct experiments on two benchmarks, including CIFAR10 and NUS-WIDE, to demonstrate the effectiveness and generality of our SNR distance metric. Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning |
| Signed Distance-based Deep Memory Recommender | Personalized recommendation algorithms learn a user’s preference for an item by measuring a distance/similarity between them. However, some of the existing recommendation models (e.g., matrix factorization) assume a linear relationship between the user and item. This approach limits the capacity of recommender systems, since the interactions between users and items in real-world applications are much more complex than the linear relationship. To overcome this limitation, in this paper, we design and propose a deep learning framework called Signed Distance-based Deep Memory Recommender, which captures non-linear relationships between users and items explicitly and implicitly, and work well in both general recommendation task and shopping basket-based recommendation task. Through an extensive empirical study on six real-world datasets in the two recommendation tasks, our proposed approach achieved significant improvement over ten state-of-the-art recommendation models. |
| Signed Heterogeneous Information Network Embedding (SHINE) |
In online social networks people often express attitudes towards others, which forms massive sentiment links among users. Predicting the sign of sentiment links is a fundamental task in many areas such as personal advertising and public opinion analysis. Previous works mainly focus on textual sentiment classification, however, text information can only disclose the ‘tip of the iceberg’ about users’ true opinions, of which the most are unobserved but implied by other sources of information such as social relation and users’ profile. To address this problem, in this paper we investigate how to predict possibly existing sentiment links in the presence of heterogeneous information. First, due to the lack of explicit sentiment links in mainstream social networks, we establish a labeled heterogeneous sentiment dataset which consists of users’ sentiment relation, social relation and profile knowledge by entity-level sentiment extraction method. Then we propose a novel and flexible end-to-end Signed Heterogeneous Information Network Embedding (SHINE) framework to extract users’ latent representations from heterogeneous networks and predict the sign of unobserved sentiment links. SHINE utilizes multiple deep autoencoders to map each user into a low-dimension feature space while preserving the network structure. We demonstrate the superiority of SHINE over state-of-the-art baselines on link prediction and node recommendation in two real-world datasets. The experimental results also prove the efficacy of SHINE in cold start scenario. |
| Significance-Offset Convolutional Neural Network | We propose ‘Significance-Offset Convolutional Neural Network’, a deep convolutional network architecture for multivariate time series regression. The model is inspired by standard autoregressive (AR) models and gating mechanisms used in recurrent neural networks. It involves an AR-like weighting system, where the final predictor is obtained as a weighted sum of sub-predictors while the weights are data-dependent functions learnt through a convolutional network.The architecture was designed for applications on asynchronous time series with low signal-to-noise ratio and hence is evaluated on such datasets: a hedge fund proprietary dataset of over2 million quotes for a credit derivative index andan artificially generated noisy autoregressive series. The proposed architecture achieves promising results compared to convolutional and recur-rent neural networks. The code for the numerical experiments and the architecture implementation will be shared online to make the research reproducible. |
| Signuology | Signuology is defined as the study of sets of characteristic predictive signals contained within data in the form of combined features of the data that are characteristic of an observation of interest within the data. The terms data mining and data structure imply rigid and discrete characteristics. A signal has more flexibility, borrowing from ideas contained in the superposition principle in physics. One can take the same data and ask a difference question, a different dependent variable, and find a different signal; the data structure will be the same. Data structure as a high level concept appears to limit one’s thinking. Feature engineering is an activity within signuology. These signals allow for a flexibility not afforded in the thinking implied by the terms data structure and data mining. |
| SigOpt Orchestrate | Two key factors dominate the development of effective production grade machine learning models. First, it requires a local software implementation and iteration process. Second, it requires distributed infrastructure to efficiently conduct training and hyperparameter optimization. While modern machine learning frameworks are very effective at the former, practitioners are often left building ad hoc frameworks for the latter. We present SigOpt Orchestrate, a library for such simultaneous training in a cloud environment. We describe the motivating factors and resulting design of this library, feedback from initial testing, and future goals. |
| Silander-Myllymaki | bnstruct |
| Silent Choir | The cost of communication is a substantial factor affecting the scalability of many distributed applications. Every message sent can incur a cost in storage, computation, energy and bandwidth. Consequently, reducing the communication costs of distributed applications is highly desirable. The best way to reduce message costs is by communicating without sending any messages whatsoever. This paper initiates a rigorous investigation into the use of silence in synchronous settings, in which processes can fail. We formalize sufficient conditions for information transfer using silence, as well as necessary conditions for particular cases of interest. This allows us to identify message patterns that enable communication through silence. In particular, a pattern called a {\em silent choir} is identified, and shown to be central to information transfer via silence in failure-prone systems. The power of the new framework is demonstrated on the {\em atomic commitment} problem (AC). A complete characterization of the tradeoff between message complexity and round complexity in the synchronous model with crash failures is provided, in terms of lower bounds and matching protocols. In particular, a new message-optimal AC protocol is designed using silence, in which processes decide in~3 rounds in the common case. This significantly improves on the best previously known message-optimal AC protocol, in which decisions were performed in $\Theta(n)$ rounds. |
| Silhouette | Silhouette refers to a method of interpretation and validation of clusters of data. The technique provides a succinct graphical representation of how well each object lies within its cluster. It was first described by Peter J. Rousseeuw in 1986. cluster |
| SimBlock | Blockchain, which is a technology for distributedly managing ledger information over multiple nodes without a centralized system, has elicited increasing attention. Performing experiments on actual blockchains are difficult because a large number of nodes in wide areas are necessary. In this study, we developed a blockchain network simulator SimBlock for such experiments. Unlike the existing simulators, SimBlock can easily change behavior of node, so that it enables to investigate the influence of nodes’ behavior on blockchains. We compared some simulation results with the measured values in actual blockchains to demonstrate the validity of this simulator. Furthermore, to show practical usage, we conducted two experiments which clarify the influence of neighbor node selection algorithms and relay networks on the block propagation time. The simulator could depict the effects of the two techniques on block propagation time. The simulator will be publicly available in a few months. |
| SimDex | We present SimDex, a new technique for serving exact top-K recommendations on matrix factorization models that measures and optimizes for the similarity between users in the model. Previous serving techniques presume a high degree of similarity (e.g., L2 or cosine distance) among users and/or items in MF models; however, as we demonstrate, the most accurate models are not guaranteed to exhibit high similarity. As a result, brute-force matrix multiply outperforms recent proposals for top-K serving on several collaborative filtering tasks. Based on this observation, we develop SimDex, a new technique for serving matrix factorization models that automatically optimizes serving based on the degree of similarity between users, and outperforms existing methods in both the high-similarity and low-similarity regimes. SimDexfirst measures the degree of similarity among users via clustering and uses a cost-based optimizer to either construct an index on the model or defer to blocked matrix multiply. It leverages highly efficient linear algebra primitives in both cases to deliver predictions either from its index or from brute-force multiply. Overall, SimDex runs an average of 2x and up to 6x faster than highly optimized baselines for the most accurate models on several popular collaborative filtering datasets. |
| Simhash Algorithm | Most hash functions are used to separate and obscure data, so that similar data hashes to very different keys. We propose to use hash functions for the opposite purpose: to detect similarities between data. Detecting similar files and classifying documents is a well-studied problem, but typically involves complex heuristics and/or O(n 2 ) pair-wise comparisons. Using a hash function that hashed similar files to similar values, file similarity could be determined simply by comparing pre-sorted hash key values. The challenge is to find a similarity hash that minimizes false positives. We have implemented a family of similarity hash functions with this intent. We have further enhanced their performance by storing the auxiliary data used to compute our hash keys. This data is used as a second filter after a hash key comparison indicates that two files are potentially similar. We use these tests to explore the notion of ‘similarity.’ GitXiv |
| Similar Unlabelled Classification (SU Classification) |
One of the biggest bottlenecks in supervised learning is its high labeling cost. To overcome this problem, we propose a new weakly-supervised learning setting called SU classification, where only similar (S) data pairs (two examples belong to the same class) and unlabeled (U) data are needed, instead of fully-supervised data. We show that an unbiased estimator of the classification risk can be obtained only from SU data, and its empirical risk minimizer achieves the optimal parametric convergence rate. Finally, we demonstrate the effectiveness of the proposed method through experiments. |
| Similarity Ensemble Approach (SEA) |
SEA is based on the idea that two targets are similar if the ligand sets of a target are similar to one another. The similarity of two ligand sets is computed by the sum of ligand pair similarities that exceed a certain threshold. The ligand pair similarity is measured by Tanimoto similarity. To correct for size or chemical composition bias a correction technique is intrudiced, which is based on the similarity obtained from randomly drawn ligand sets is. This leads to z-scores for similarity between the sets. It is argued that the z-scores conform an extreme value distribution. Using this extreme value distribution the probability that a compound is active on a certain target is calculated by assuming that one of the two ligand sets consists only of the compound to predict. We implemented the SEA method efficiently for using it on a multi-core supercomputer, enabling us to compare it to the other target prediction methods. |
| Similarity Flooding | Matching elements of two data schemas or two data instances plays a key role in data warehousing, e-business, or even biochemical applications. In this paper we present a matching algorithm based on a fixpoint computation that is usable across different scenarios. The algorithm takes two graphs (schemas, catalogs, or other data structures) as input, and produces as output a mapping between corresponding nodes of the graphs. Depending on the matching goal, a subset of the mapping is chosen using filters. After our algorithm runs, we expect a human to check and if necessary adjust the results. As a matter of fact, we evaluate the ‘accuracy’ of the algorithm by counting the number of needed adjustments. We conducted a user study, in which our accuracy metric was used to estimate the labor savings that the users could obtain by utilizing our algorithm to obtain an initial matching. Finally, we illustrate how our matching algorithm is deployed as one of several high-level operators in an implemented testbed for managing information models and mappings. |
| Similarity-Based Imbalanced Classification (SBIC) |
When the training data in a two-class classification problem is overwhelmed by one class, most classification techniques fail to correctly identify the data points belonging to the underrepresented class. We propose Similarity-based Imbalanced Classification (SBIC) that learns patterns in the training data based on an empirical similarity function. To take the imbalanced structure of the training data into account, SBIC utilizes the concept of absent data, i.e. data from the minority class which can help better find the boundary between the two classes. SBIC simultaneously optimizes the weights of the empirical similarity function and finds the locations of absent data points. As such, SBIC uses an embedded mechanism for synthetic data generation which does not modify the training dataset, but alters the algorithm to suit imbalanced datasets. Therefore, SBIC uses the ideas of both major schools of thoughts in imbalanced classification: Like cost-sensitive approaches SBIC operates on an algorithm level to handle imbalanced structures; and similar to synthetic data generation approaches, it utilizes the properties of unobserved data points from the minority class. The application of SBIC to imbalanced datasets suggests it is comparable to, and in some cases outperforms, other commonly used classification techniques for imbalanced datasets. |
| Similarity-based Random Survival Forest | Predicting the time to a clinical outcome for patients in intensive care units (ICUs) helps to support critical medical treatment decisions. The time to an event of interest could be, for example, survival time or time to recovery from a disease/ailment observed within the ICU. The massive health datasets generated from the uptake of Electronic Health Records (EHRs) are diverse in variety as patients can be quite dissimilar in their relationship between the feature vector and the outcome, adding more noise than information to prediction. We propose a modified random forest method for survival data that identifies similar cases and improves prediction accuracy. We also introduce an adaptation of our methodology in the case of dependent censoring. Our proposed method is demonstrated in the Medical Information Mart for Intensive Care (MIMIC-III) database, and we also present properties of our methodology through a comprehensive simulation study. Introducing similarity to the random survival forest method indeed provides additional predictive accuracy compared to random survival forest alone in the various analyses we undertook. |
| Similarity-First Search Seriation (SFS) |
SFS |
| Simion Zoo | We present Simion Zoo, a Reinforcement Learning (RL) workbench that provides a complete set of tools to design, run, and analyze the results,both statistically and visually, of RL control applications. The main features that set apart Simion Zoo from similar software packages are its easy-to-use GUI, its support for distributed execution including deployment over graphics processing units (GPUs) , and the possibility to explore concurrently the RL metaparameter space, which is key to successful RL experimentation. |
| Simple Competitive Learning (SCL) |
|
| Simple Logging Facade for Java (SLF4J) |
The Simple Logging Facade for Java (SLF4J) serves as a simple facade or abstraction for various logging frameworks (e.g. java.util.logging, logback, log4j) allowing the end user to plug in the desired logging framework at deployment time. Before you start using SLF4J, we highly recommend that you read the two-page SLF4J user manual. Note that SLF4J-enabling your library implies the addition of only a single mandatory dependency, namely slf4j-api.jar. If no binding is found on the class path, then SLF4J will default to a no-operation implementation. In case you wish to migrate your Java source files to SLF4J, consider our migrator tool which can migrate your project to use the SLF4J API in just a few minutes. In case an externally-maintained component you depend on uses a logging API other than SLF4J, such as commons logging, log4j or java.util.logging, have a look at SLF4J’s binary-support for legacy APIs. |
| Simple Probabilistic Inverse (SPI) |
Spectral topic modeling algorithms operate on matrices/tensors of word co-occurrence statistics to learn topic-specific word distributions. This approach removes the dependence on the original documents and produces substantial gains in efficiency and provable topic inference, but at a cost: the model can no longer provide information about the topic composition of individual documents. Recently Thresholded Linear Inverse (TLI) is proposed to map the observed words of each document back to its topic composition. However, its linear characteristics limit the inference quality without considering the important prior information over topics. In this paper, we evaluate Simple Probabilistic Inverse (SPI) method and novel Prior-aware Dual Decomposition (PADD) that is capable of learning document-specific topic compositions in parallel. Experiments show that PADD successfully leverages topic correlations as a prior, notably outperforming TLI and learning quality topic compositions comparable to Gibbs sampling on various data. |
| Simple Stochastic Recursive Gradient Descent (SSRGD) |
We analyze stochastic gradient algorithms for optimizing nonconvex problems. In particular, our goal is to find local minima (second-order stationary points) instead of just finding first-order stationary points which may be some bad unstable saddle points. We show that a simple perturbed version of stochastic recursive gradient descent algorithm (called SSRGD) can find an $(\epsilon,\delta)$-second-order stationary point with $\widetilde{O}(\sqrt{n}/\epsilon^2 + \sqrt{n}/\delta^4 + n/\delta^3)$ stochastic gradient complexity for nonconvex finite-sum problems. As a by-product, SSRGD finds an $\epsilon$-first-order stationary point with $O(n+\sqrt{n}/\epsilon^2)$ stochastic gradients. These results are almost optimal since Fang et al. [2018] provided a lower bound $\Omega(\sqrt{n}/\epsilon^2)$ for finding even just an $\epsilon$-first-order stationary point. We emphasize that SSRGD algorithm for finding second-order stationary points is as simple as for finding first-order stationary points just by adding a uniform perturbation sometimes, while all other algorithms for finding second-order stationary points with similar gradient complexity need to combine with a negative-curvature search subroutine (e.g., Neon2 [Allen-Zhu and Li, 2018]). Moreover, the simple SSRGD algorithm gets a simpler analysis. Besides, we also extend our results from nonconvex finite-sum problems to nonconvex online (expectation) problems, and prove the corresponding convergence results. |
| Simple Temporal Point Process (SPP) |
A simple temporal point process (SPP) is an important class of time series, where the sample realization of the process is solely composed of the times at which events occur. Particular examples of point process data are neuronal spike patterns or spike trains, and a large number of distance and similarity metrics for those data have been proposed. A marked point process (MPP) is an extension of a simple temporal point process, in which a certain vector valued mark is associated with each of the temporal points in the SPP. Analyses of MPPs are of practical importance because instances of MPPs include recordings of natural disasters such as earthquakes and tornadoes. mmpp |
| SimpleDet | Object detection and instance recognition play a central role in many AI applications like autonomous driving, video surveillance and medical image analysis. However, training object detection models on large scale datasets remains computationally expensive and time consuming. This paper presents an efficient and open source object detection framework called SimpleDet which enables the training of state-of-the-art detection models on consumer grade hardware at large scale. SimpleDet supports up-to-date detection models with best practice. SimpleDet also supports distributed training with near linear scaling out of box. Codes, examples and documents of SimpleDet can be found at https://…/simpledet . |
| Simplex Algorithm | In mathematical optimization, Dantzig’s simplex algorithm (or simplex method) is a popular algorithm for linear programming. |
| Simplex Model | |
| Simplified Probabilistic Linear Discriminant Analysis (SPLDA) |
|
| Simplified Shotgun Stochastic Search (S5) |
In p >> n settings, full posterior sampling using existing Markov chain Monte Carlo (MCMC) algorithms is highly inefficient and often not feasible from a practical perspective. To overcome this problem, we propose a scalable stochastic search algorithm that is called the Simplified Shotgun Stochastic Search (S5) and aimed at rapidly explore interesting regions of model space and finding the maximum a posteriori(MAP) model. Also, the S5 provides an approximation of posterior probability of each model (including the marginal inclusion probabilities). BayesS5 |
| SimpNet | Major winning Convolutional Neural Networks (CNNs), such as VGGNet, ResNet, DenseNet, \etc, include tens to hundreds of millions of parameters, which impose considerable computation and memory overheads. This limits their practical usage in training and optimizing for real-world applications. On the contrary, light-weight architectures, such as SqueezeNet, are being proposed to address this issue. However, they mainly suffer from low accuracy, as they have compromised between the processing power and efficiency. These inefficiencies mostly stem from following an ad-hoc designing procedure. In this work, we discuss and propose several crucial design principles for an efficient architecture design and elaborate intuitions concerning different aspects of the design procedure. Furthermore, we introduce a new layer called {\it SAF-pooling} to improve the generalization power of the network while keeping it simple by choosing best features. Based on such principles, we propose a simple architecture called {\it SimpNet}. We empirically show that SimpNet provides a good trade-off between the computation/memory efficiency and the accuracy solely based on these primitive but crucial principles. SimpNet outperforms the deeper and more complex architectures such as VGGNet, ResNet, WideResidualNet \etc, on several well-known benchmarks, while having 2 to 25 times fewer number of parameters and operations. We obtain state-of-the-art results (in terms of a balance between the accuracy and the number of involved parameters) on standard datasets, such as CIFAR10, CIFAR100, MNIST and SVHN. The implementations are available at \href{url}{https://…/SimpNet}. |
| Simpson’s Paradox | In probability and statistics, Simpson’s paradox, or the Yule-Simpson effect, is a paradox in which a trend that appears in different groups of data disappears when these groups are combined, and the reverse trend appears for the aggregate data. This result is often encountered in social-science and medical-science statistics, and is particularly confounding when frequency data are unduly given causal interpretations. Simpson’s Paradox disappears when causal relations are brought into consideration. Many statisticians believe that the mainstream public should be informed of the counter-intuitive results in statistics such as Simpson’s paradox. http://…/confounding.html |
| SimRank | SimRank is a general similarity measure, based on a simple and intuitive graph-theoretic model. SimRank is applicable in any domain with object-to-object relationships, that measures similarity of the structural context in which objects occur, based on their relationships with other objects. Effectively, SimRank is a measure that says “two objects are considered to be similar if they are referenced by similar objects.” |
| Simulated Annealing (SA) |
Simulated annealing (SA) is a generic probabilistic metaheuristic for the global optimization problem of locating a good approximation to the global optimum of a given function in a large search space. It is often used when the search space is discrete (e.g., all tours that visit a given set of cities). For certain problems, simulated annealing may be more efficient than exhaustive enumeration – provided that the goal is merely to find an acceptably good solution in a fixed amount of time, rather than the best possible solution. |
| Simulated Policy Learning (SimPLe) |
Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction — substantially more, in fact, than a human would need to learn the same games. How can people learn so quickly? Part of the answer may be that people can learn how the game works and predict which actions will lead to desirable outcomes. In this paper, we explore how video prediction models can similarly enable agents to solve Atari games with orders of magnitude fewer interactions than model-free methods. We describe Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models and present a comparison of several model architectures, including a novel architecture that yields the best results in our setting. Our experiments evaluate SimPLe on a range of Atari games and achieve competitive results with only 100K interactions between the agent and the environment (400K frames), which corresponds to about two hours of real-time play. |
| Simulator-Augmented Interaction Network (SAIN) |
Physics engines play an important role in robot planning and control; however, many real-world control problems involve complex contact dynamics that cannot be characterized analytically. Most physics engines therefore employ . approximations that lead to a loss in precision. In this paper, we propose a hybrid dynamics model, simulator-augmented interaction networks (SAIN), combining a physics engine with an object-based neural network for dynamics modeling. Compared with existing models that are purely analytical or purely data-driven, our hybrid model captures the dynamics of interacting objects in a more accurate and data-efficient manner.Experiments both in simulation and on a real robot suggest that it also leads to better performance when used in complex control tasks. Finally, we show that our model generalizes to novel environments with varying object shapes and materials. |
| simultaneous Coherent Structure Coloring (sCSC) |
Existing methods that aim to automatically cluster data into physically meaningful subsets typically require assumptions regarding the number, size, or shape of the coherent subgroups. We present a new method, simultaneous Coherent Structure Coloring (sCSC), which accomplishes the task of unsupervised clustering without a priori guidance regarding the underlying structure of the data. To illustrate the versatility of the method, we apply it to frontier physics problems at vastly different temporal and spatial scales: in a theoretical model of geophysical fluid dynamics, in laboratory measurements of vortex ring formation and entrainment, and in atomistic simulation of the Protein G system. The theoretical flow involves sparse sampling of non-equilibrium dynamics, where this new technique can find and characterize the structures that govern fluid transport using two orders of magnitude less data than required by existing methods. Application of the method to empirical measurements of vortex formation leads to the discovery of a well defined region in which vortex ring entrainment occurs, with potential implications ranging from flow control to cardiovascular diagnostics. Finally, the protein folding example demonstrates a data-rich application governed by equilibrium dynamics, where the technique in this manuscript automatically discovers the hierarchy of distinct processes that govern protein folding and clusters protein configurations accordingly. We anticipate straightforward translation to many other fields where existing analysis tools, such as k-means and traditional hierarchical clustering, require ad hoc assumptions on the data structure or lack the interpretability of the present method. The method is also potentially generalizable to fields where the underlying processes are less accessible, such as genomics and neuroscience. |
| Simultaneous Mean-Variance Regression | We propose simultaneous mean-variance regression for the linear estimation and approximation of conditional mean functions. In the presence of heteroskedasticity of unknown form, our method accounts for varying dispersion in the regression outcome across the support of conditioning variables by using weights that are jointly determined with mean regression parameters. Simultaneity generates outcome predictions that are guaranteed to improve over ordinary least-squares prediction error, with corresponding parameter standard errors that are automatically valid. Under shape misspecification of the conditional mean and variance functions, we establish existence and uniqueness of the resulting approximations and characterize their formal interpretation. We illustrate our method with numerical simulations and two empirical applications to the estimation of the relationship between economic prosperity in 1500 and today, and demand for gasoline in the United States. |
| Simultaneous Perturbation Stochastic Approximation (SPSA) |
This manuscript presents the following: (1) an improved version of the Binary Simultaneous Perturbation Stochastic Approximation (SPSA) Method for feature selection in machine learning (Aksakalli and Malekipirbazari, Pattern Recognition Letters, Vol. 75, 2016) based on non-monotone iteration gains computed via the Barzilai and Borwein (BB) method, (2) its adaptation for feature ranking, and (3) comparison against popular methods on public benchmark datasets. The improved method, which we call SPSA-FSR, dramatically reduces the number of iterations required for convergence without impacting solution quality. SPSA-FSR can be used for feature ranking and feature selection both for classification and regression problems. After a review of the current state-of-the-art, we discuss our improvements in detail and present three sets of computational experiments: (1) comparison of SPSA-FS as a (wrapper) feature selection method against sequential methods as well as genetic algorithms, (2) comparison of SPSA-FS as a feature ranking method in a classification setting against random forest importance, chi-squared, and information main methods, and (3) comparison of SPSA-FS as a feature ranking method in a regression setting against minimum redundancy maximum relevance (MRMR), RELIEF, and linear correlation methods. The number of features in the datasets we use range from a few dozens to a few thousands. Our results indicate that SPSA-FS converges to a good feature set in no more than 100 iterations and therefore it is quite fast for a wrapper method. SPSA-FS also outperforms popular feature selection as well as feature ranking methods in majority of test cases, sometimes by a large margin, and it stands as a promising new feature selection and ranking method. |
| Simultaneous Validation Over an Organized set of Hypotheses (SVOOSH) |
|
| Since Cosine Crow Search Algorithm (SCCSA) |
This paper presents a novel hybrid algorithm named Since Cosine Crow Search Algorithm. To propose the SCCSA, two novel algorithms are considered including Crow Search Algorithm (CSA) and Since Cosine Algorithm (SCA). The advantages of the two algorithms are considered and utilize to design an efficient hybrid algorithm which can perform significantly better in various benchmark functions. The combination of concept and operators of the two algorithms enable the SCCSA to make an appropriate trade-off between exploration and exploitation abilities of the algorithm. To evaluate the performance of the proposed SCCSA, seven well-known benchmark functions are utilized. The results indicated that the proposed hybrid algorithm is able to provide very competitive solution comparing to other state-of-the-art meta heuristics. |
| SincNet | Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to learn complex and abstract representations, that are progressively obtained by combining simpler ones. Nevertheless, the internal ‘black-box’ representations automatically discovered by current neural architectures often suffer from a lack of interpretability, making of primary interest the study of explainable machine learning techniques. This paper summarizes our recent efforts to develop a more interpretable neural model for directly processing speech from the raw waveform. In particular, we propose SincNet, a novel Convolutional Neural Network (CNN) that encourages the first layer to discover more meaningful filters by exploiting parametrized sinc functions. In contrast to standard CNNs, which learn all the elements of each filter, only low and high cutoff frequencies of band-pass filters are directly learned from data. This inductive bias offers a very compact way to derive a customized filter-bank front-end, that only depends on some parameters with a clear physical meaning. Our experiments, conducted on both speaker and speech recognition, show that the proposed architecture converges faster, performs better, and is more interpretable than standard CNNs. |
| Sine-Cosine Algorithm (SCA) |
This paper proposes a novel population-based optimization algorithm called Sine Cosine Algorithm (SCA) for solving optimization problems. The SCA creates multiple initial random candidate solutions and requires them to fluctuate outwards or towards the best solution using a mathematical model based on sine and cosine functions. Several random and adaptive variables also are integrated to this algorithm to emphasize exploration and exploitation of the search space in different milestones of optimization. The performance of SCA is benchmarked in three test phases. Firstly, a set of well-known test cases including unimodal, multi-modal, and composite functions are employed to test exploration, exploitation, local optima avoidance, and convergence of SCA. Secondly, several performance metrics (search history, trajectory, average fitness of solutions, and the best solution during optimization) are used to qualitatively observe and confirm the performance of SCA on shifted two-dimensional test functions. Finally, the cross-section of an aircraft’s wing is optimized by SCA as a real challenging case study to verify and demonstrate the performance of this algorithm in practice. The results of test functions and performance metrics prove that the algorithm proposed is able to explore different regions of a search space, avoid local optima, converge towards the global optimum, and exploit promising regions of a search space during optimization effectively. The SCA algorithm obtains a smooth shape for the airfoil with a very low drag, which demonstrates that this algorithm can highly be effective in solving real problems with constrained and unknown search spaces. Note that the source codes of the SCA algorithm are publicly available at http://…/SCA.html. |
| SinGAN | We introduce SinGAN, an unconditional generative model that can be learned from a single natural image. Our model is trained to capture the internal distribution of patches within the image, and is then able to generate high quality, diverse samples that carry the same visual content as the image. SinGAN contains a pyramid of fully convolutional GANs, each responsible for learning the patch distribution at a different scale of the image. This allows generating new samples of arbitrary size and aspect ratio, that have significant variability, yet maintain both the global structure and the fine textures of the training image. In contrast to previous single image GAN schemes, our approach is not limited to texture images, and is not conditional (i.e. it generates samples from noise). User studies confirm that the generated samples are commonly confused to be real images. We illustrate the utility of SinGAN in a wide range of image manipulation tasks. |
| Single Document Summarization | Single document summarization is the task of producing a shorter version of a document while preserving its principal information content. Ranking Sentences for Extractive Summarization with Reinforcement Learning |
| Single Hidden-layer Feedforward Neural Network (SLFN) |
Training and predict functions for Single Hidden-layer Feedforward Neural Networks (SLFN) using the Extreme Learning Machine (ELM) algorithm. The ELM algorithm differs from the traditional gradient-based algorithms for very short training times (it doesn’t need any iterative tuning, this makes learning time very fast) and there is no need to set any other parameters like learning rate, momentum, epochs, etc. This is a reimplementation of the ‘elmNN’ package using ‘RcppArmadillo’ after the ‘elmNN’ package was archived. For more information, see ‘Extreme learning machine: Theory and applications’ by Guang-Bin Huang, Qin-Yu Zhu, Chee-Kheong Siew (2006), Elsevier B.V, <doi:10.1016/j.neucom.2005.12.126>. elmNNRcpp |
| Single Image Super-Resolution | Deep Learning for Single Image Super-Resolution: A Brief Review |
| Single Index Latent Variable Models (SILVar) |
A semi-parametric, non-linear regression model in the presence of latent variables is introduced. These latent variables can correspond to unmodeled phenomena or unmeasured agents in a complex networked system. This new formulation allows joint estimation of certain non-linearities in the system, the direct interactions between measured variables, and the effects of unmodeled elements on the observed system. The particular form of the model is justified, and learning is posed as a regularized maximum likelihood estimation. This leads to classes of structured convex optimization problems with a ‘sparse plus low-rank’ flavor. Relations between the proposed model and several common model paradigms, such as those of Robust Principal Component Analysis (PCA) and Vector Autoregression (VAR), are established. Particularly in the VAR setting, the low-rank contributions can come from broad trends exhibited in the time series. Details of the algorithm for learning the model are presented. Experiments demonstrate the performance of the model and the estimation algorithm on simulated and real data. |
| Single Shot Multibox Detetor (SSD) |
We present a method for detecting objects in images using a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location. At prediction time, the network generates scores for the presence of each object category in each default box and produces adjustments to the box to better match the object shape. Additionally, the network combines predictions from multiple feature maps with different resolutions to naturally handle objects of various sizes. Our SSD model is simple relative to methods that require object proposals because it completely eliminates proposal generation and subsequent pixel or feature resampling stage and encapsulates all computation in a single network. This makes SSD easy to train and straightforward to integrate into systems that require a detection component. Experimental results on the PASCAL VOC, MS COCO, and ILSVRC datasets confirm that SSD has comparable accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference. Compared to other single stage methods, SSD has much better accuracy, even with a smaller input image size. For input, SSD achieves 72.1% mAP on VOC2007 test at 58 FPS on a Nvidia Titan X and for input, SSD achieves 75.1% mAP, outperforming a comparable state of the art Faster R-CNN model. Code is available at this https URL . |
| Single-Equation Penalized Error Correction Selector (SPECS) |
In this paper we propose the Single-equation Penalized Error Correction Selector (SPECS) as an automated estimation procedure for dynamic single-equation models with a large number of potentially (co)integrated variables. By extending the classical single-equation error correction model, SPECS enables the researcher to model large cointegrated datasets without necessitating any form of pre-testing for the order of integration or cointegrating rank. We show that SPECS is able to consistently estimate an appropriate linear combination of the cointegrating vectors that may occur in the underlying DGP, while simultaneously enabling the correct recovery of sparsity patterns in the corresponding parameter space. A simulation study shows strong selective capabilities, as well as superior predictive performance in the context of nowcasting compared to high-dimensional models that ignore cointegration. An empirical application to nowcasting Dutch unemployment rates using Google Trends confirms the strong practical performance of our procedure. |
| SingleGAN | Image translation is a burgeoning field in computer vision where the goal is to learn the mapping between an input image and an output image. However, most recent methods require multiple generators for modeling different domain mappings, which are inefficient and ineffective on some multi-domain image translation tasks. In this paper, we propose a novel method, SingleGAN, to perform multi-domain image-to-image translations with a single generator. We introduce the domain code to explicitly control the different generative tasks and integrate multiple optimization goals to ensure the translation. Experimental results on several unpaired datasets show superior performance of our model in translation between two domains. Besides, we explore variants of SingleGAN for different tasks, including one-to-many domain translation, many-to-many domain translation and one-to-one domain translation with multimodality. The extended experiments show the universality and extensibility of our model. |
| Single-Linkage Clustering | Single-linkage clustering is one of several methods of agglomerative hierarchical clustering. In the beginning of the process, each element is in a cluster of its own. The clusters are then sequentially combined into larger clusters, until all elements end up being in the same cluster. At each step, the two clusters separated by the shortest distance are combined. The definition of ‘shortest distance’ is what differentiates between the different agglomerative clustering methods. In single-linkage clustering, the link between two clusters is made by a single element pair, namely those two elements (one in each cluster) that are closest to each other. The shortest of these links that remains at any step causes the fusion of the two clusters whose elements are involved. The method is also known as nearest neighbour clustering. The result of the clustering can be visualized as a dendrogram, which shows the sequence of cluster fusion and the distance at which each fusion took place. |
| Single-Objective Generative Adversarial Active Learning (SO-GAAL) |
Outlier detection is an important topic in machine learning and has been used in a wide range of applications. In this paper, we approach outlier detection as a binary-classification issue by sampling potential outliers from a uniform reference distribution. However, due to the sparsity of data in high-dimensional space, a limited number of potential outliers may fail to provide sufficient information to assist the classifier in describing a boundary that can separate outliers from normal data effectively. To address this, we propose a novel Single-Objective Generative Adversarial Active Learning (SO-GAAL) method for outlier detection, which can directly generate informative potential outliers based on the mini-max game between a generator and a discriminator. Moreover, to prevent the generator from falling into the mode collapsing problem, the stop node of training should be determined when SO-GAAL is able to provide sufficient information. But without any prior information, it is extremely difficult for SO-GAAL. Therefore, we expand the network structure of SO-GAAL from a single generator to multiple generators with different objectives (MO-GAAL), which can generate a reasonable reference distribution for the whole dataset. We empirically compare the proposed approach with several state-of-the-art outlier detection methods on both synthetic and real-world datasets. The results show that MO-GAAL outperforms its competitors in the majority of cases, especially for datasets with various cluster types or high irrelevant variable ratio. |
| Single-Path NAS | Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Search (NAS) for ConvNet design is a challenging problem due to the combinatorially large design space and search time (at least 200 GPU-hours). To alleviate this complexity, we propose Single-Path NAS, a novel differentiable NAS method for designing device-efficient ConvNets in less than 4 hours. 1. Novel NAS formulation: our method introduces a single-path, over-parameterized ConvNet to encode all architectural decisions with shared convolutional kernel parameters. 2. NAS efficiency: Our method decreases the NAS search cost down to 8 epochs (30 TPU-hours), i.e., up to 5,000x faster compared to prior work. 3. On-device image classification: Single-Path NAS achieves 74.96% top-1 accuracy on ImageNet with 79ms inference latency on a Pixel 1 phone, which is state-of-the-art accuracy compared to NAS methods with similar latency (<80ms). |
| Singular Spectrum Analysis (SSA) |
In time series analysis, singular spectrum analysis (SSA) is a nonparametric spectral estimation method. It combines elements of classical time series analysis, multivariate statistics, multivariate geometry, dynamical systems and signal processing. Its roots lie in the classical Karhunen (1946)-Loève (1945, 1978) spectral decomposition of time series and random fields and in the Mañé (1981)-Takens (1981) embedding theorem. SSA can be an aid in the decomposition of time series into a sum of components, each having a meaningful interpretation. The name “singular spectrum analysis” relates to the spectrum of eigenvalues in a singular value decomposition of a covariance matrix, and not directly to a frequency domain decomposition. Rssa,spectral.methods |
| Singular Value Decomposition (SVD) |
In linear algebra, the singular value decomposition (SVD) is a factorization of a real or complex matrix, with many useful applications in signal processing and statistics. |
| Singular Vector Canonical Correlation Analysis (SVCCA) |
We introduce a technique based on the singular vector canonical correlation analysis (SVCCA) for measuring the generality of neural network layers across a continuously-parametrized set of tasks. We illustrate this method by studying generality in neural networks trained to solve parametrized boundary value problems based on the Poisson partial differential equation. We find that the first hidden layer is general, and that deeper layers are successively more specific. Next, we validate our method against an existing technique that measures layer generality using transfer learning experiments. We find excellent agreement between the two methods, and note that our method is much faster, particularly for continuously-parametrized problems. Finally, we visualize the general representations of the first layers, and interpret them as generalized coordinates over the input domain. |
| Singularity | Singularity is a container platform focused on supporting ‘Mobility of Compute’. Mobility of Compute encapsulates the development to compute model where developers can work in an environment of their choosing and creation, and when the developer needs additional compute resources, this environment can easily be copied and executed on other platforms. Additionally, as the primary use case for Singularity is targeted towards computational portability. Many of the barriers to entry of other container solutions do not apply to Singularity, making it an ideal solution for users (both computational and non-computational) and HPC centers. |
| Sinkhorn AutoEncoder (SAE) |
Optimal Transport offers an alternative to maximum likelihood for learning generative autoencoding models. We show how this principle dictates the minimization of the Wasserstein distance between the encoder aggregated posterior and the prior, plus a reconstruction error. We prove that in the non-parametric limit the autoencoder generates the data distribution if and only if the two distributions match exactly, and that the optimum can be obtained by deterministic autoencoders. We then introduce the Sinkhorn AutoEncoder (SAE), which casts the problem into Optimal Transport on the latent space. The resulting Wasserstein distance is minimized by backpropagating through the Sinkhorn algorithm. SAE models the aggregated posterior as an implicit distribution and therefore does not need a reparameterization trick for gradients estimation. Moreover, it requires virtually no adaptation to different prior distributions. We demonstrate its flexibility by considering models with hyperspherical and Dirichlet priors, as well as a simple case of probabilistic programming. SAE matches or outperforms other autoencoding models in visual quality and FID scores. |
| Site Reliability Engineering (SRE) |
Site Reliability Engineering (SRE) is a discipline that incorporates aspects of software engineering and applies that to IT operations problems. The main goals are to create ultra-scalable and highly reliable software systems. According to Ben Treynor, founder of Google’s Site Reliability Team, SRE is ‘what happens when a software engineer is tasked with what used to be called operations.’ Site Reliability Engineering was created at Google around 2003 when Ben Treynor was hired to lead a team of seven software engineers to run a production environment. The team was tasked to make Google’s sites run smoothly, efficiently, and more reliably. Early on, Google’s large-scale systems required the company to come up with new paradigms on how to manage such large systems and at the same time introduce new features continuously but at a very high-quality end user experience. The SRE footprint at Google is now larger than 1500 engineers. Many products have small to medium sized SRE teams supporting them, though by far not all products have SREs. The SRE processes that have been honed over the years are being used by other, mainly large scale, companies that are also starting to implement this paradigm. ServiceNow, Microsoft, Apple, Twitter, Facebook, Dropbox, Amazon, Target, Dell Technologies, IBM, Xero, Oracle, Zalando, Acquia, VMware and GitHub have all put together SRE teams. |
| Sitting Closer to Friends than Enemies (SCFE) |
The Sitting Closer to Friends than Enemies (SCFE) problem is to find an embedding in a metric space for the vertices of a given signed graph so that, for every pair of incident edges with different sign, the positive edge is shorter (in the metric of the space) than the negative edge. |
| SkeGAN | Sketching is more fundamental to human cognition than speech. Deep Neural Networks (DNNs) have achieved the state-of-the-art in speech-related tasks but have not made significant development in generating stroke-based sketches a.k.a sketches in vector format. Though there are Variational Auto Encoders (VAEs) for generating sketches in vector format, there is no Generative Adversarial Network (GAN) architecture for the same. In this paper, we propose a standalone GAN architecture SkeGAN and a VAE-GAN architecture VASkeGAN, for sketch generation in vector format. SkeGAN is a stochastic policy in Reinforcement Learning (RL), capable of generating both multidimensional continuous and discrete outputs. VASkeGAN hybridizes a VAE and a GAN, in order to couple the efficient representation of data by VAE with the powerful generating capabilities of a GAN, to produce visually appealing sketches. We also propose a new metric called the Ske-score which quantifies the quality of vector sketches. We have validated that SkeGAN and VASkeGAN generate visually appealing sketches by using Human Turing Test and Ske-score. |
| Skellam Distribution | The Skellam distribution is the discrete probability distribution of the difference n_1-n_2 of two statistically independent random variables N_1 and N_2 each having Poisson distributions with different expected values \mu_1 and \mu_2. It is useful in describing the statistics of the difference of two images with simple photon noise, as well as describing the point spread distribution in sports where all scored points are equal, such as baseball, hockey and soccer. The distribution is also applicable to a special case of the difference of dependent Poisson random variables, but just the obvious case where the two variables have a common additive random contribution which is cancelled by the differencing: see Karlis & Ntzoufras (2003) for details and an application. skellam |
| Sketch, Shingle, & Hashing (SSH) |
Similarity search on time series is a frequent operation in large-scale data-driven applications. Sophisticated similarity measures are standard for time series matching, as they are usually misaligned. Dynamic Time Warping or DTW is the most widely used similarity measure for time series because it combines alignment and matching at the same time. However, the alignment makes DTW slow. To speed up the expensive similarity search with DTW, branch and bound based pruning strategies are adopted. However, branch and bound based pruning are only useful for very short queries (low dimensional time series), and the bounds are quite weak for longer queries. Due to the loose bounds branch and bound pruning strategy boils down to a brute-force search. To circumvent this issue, we design SSH (Sketch, Shingle, & Hashing), an efficient and approximate hashing scheme which is much faster than the state-of-the-art branch and bound searching technique: the UCR suite. SSH uses a novel combination of sketching, shingling and hashing techniques to produce (probabilistic) indexes which align (near perfectly) with DTW similarity measure. The generated indexes are then used to create hash buckets for sub-linear search. Our results show that SSH is very effective for longer time sequence and prunes around 95% candidates, leading to the massive speedup in search with DTW. Empirical results on two large-scale benchmark time series data show that our proposed method can be around 20 times faster than the state-of-the-art package (UCR suite) without any significant loss in accuracy. |
| Sketched Subspace Clustering (Sketch-SC) |
The immense amount of daily generated and communicated data presents unique challenges in their processing. Clustering, the grouping of data without the presence of ground-truth labels, is an important tool for drawing inferences from data. Subspace clustering (SC) is a relatively recent method that is able to successfully classify nonlinearly separable data in a multitude of settings. In spite of their high clustering accuracy, SC methods incur prohibitively high computational complexity when processing large volumes of high-dimensional data. Inspired by random sketching approaches for dimensionality reduction, the present paper introduces a randomized scheme for SC, termed Sketch-SC, tailored for large volumes of high-dimensional data. Sketch-SC accelerates the computationally heavy parts of state-of-the-art SC approaches by compressing the data matrix across both dimensions using random projections, thus enabling fast and accurate large-scale SC. Performance analysis as well as extensive numerical tests on real data corroborate the potential of Sketch-SC and its competitive performance relative to state-of-the-art scalable SC approaches. |
| Skew Logistic Distribution | A random variable X is said to have Azzalini’s skew-logistic distribution if its pdf is f(x)=2g(x)G(lambda*x), where g(·) and G(·), respectively, denote the pdf and cdf of the logistic distribution. glogis,sld |
| Skill2vec | Un-supervise learned word embeddings have seen tremendous success in numerous Natural Language Processing (NLP) tasks in recent years. The main contribution of this paper is to develop a technique called Skill2vec, which applies machine learning techniques in recruitment to enhance the search strategy to find the candidates who possess the right skills. Skill2vec is a neural network architecture which inspired by Word2vec, developed by Mikolov et al. in 2013, to transform a skill to a new vector space. This vector space has the characteristics of calculation and present their relationship. We conducted an experiment using AB testing in a recruitment company to demonstrate the effectiveness of our approach. |
| Skilled Experience Catalogue (SEC) |
In this paper, we introduce a skill-balancing mechanism for adversarial non-player characters (NPCs), called Skilled Experience Catalogue (SEC). The objective of this mechanism is to approximately match the skill level of an NPC to an opponent in real-time. We test the technique in the context of a First-Person Shooter (FPS) game. Specifically, the technique adjusts a reinforcement learning NPC’s proficiency with a weapon based on its current performance against an opponent. Firstly, a catalogue of experience, in the form of stored learning policies, is built up by playing a series of training games. Once the NPC has been sufficiently trained, the catalogue acts as a timeline of experience with incremental knowledge milestones in the form of stored learning policies. If the NPC is performing poorly, it can jump to a later stage in the learning timeline to be equipped with more informed decision-making. Likewise, if it is performing significantly better than the opponent, it will jump to an earlier stage. The NPC continues to learn in real-time using reinforcement learning but its policy is adjusted, as required, by loading the most suitable milestones for the current circumstances. |
| SkinnerDB | SkinnerDB is designed from the ground up for reliable join ordering. It maintains no data statistics and uses no cost or cardinality models. Instead, it uses reinforcement learning to learn optimal join orders on the fly, during the execution of the current query. To that purpose, we divide the execution of a query into many small time slices. Different join orders are tried in different time slices. We merge result tuples generated according to different join orders until a complete result is obtained. By measuring execution progress per time slice, we identify promising join orders as execution proceeds. Along with SkinnerDB, we introduce a new quality criterion for query execution strategies. We compare expected execution cost against execution cost for an optimal join order. SkinnerDB features multiple execution strategies that are optimized for that criterion. Some of them can be executed on top of existing database systems. For maximal performance, we introduce a customized execution engine, facilitating fast join order switching via specialized multi-way join algorithms and tuple representations. We experimentally compare SkinnerDB’s performance against various baselines, including MonetDB, Postgres, and adaptive processing methods. We consider various benchmarks, including the join order benchmark and TPC-H variants with user-defined functions. Overall, the overheads of reliable join ordering are negligible compared to the performance impact of the occasional, catastrophic join order choice. |
| Skip-GANomaly | Despite inherent ill-definition, anomaly detection is a research endeavor of great interest within machine learning and visual scene understanding alike. Most commonly, anomaly detection is considered as the detection of outliers within a given data distribution based on some measure of normality. The most significant challenge in real-world anomaly detection problems is that available data is highly imbalanced towards normality (i.e. non-anomalous) and contains a most a subset of all possible anomalous samples – hence limiting the use of well-established supervised learning methods. By contrast, we introduce an unsupervised anomaly detection model, trained only on the normal (non-anomalous, plentiful) samples in order to learn the normality distribution of the domain and hence detect abnormality based on deviation from this model. Our proposed approach employs an encoder-decoder convolutional neural network with skip connections to thoroughly capture the multi-scale distribution of the normal data distribution in high-dimensional image space. Furthermore, utilizing an adversarial training scheme for this chosen architecture provides superior reconstruction both within high-dimensional image space and a lower-dimensional latent vector space encoding. Minimizing the reconstruction error metric within both the image and hidden vector spaces during training aids the model to learn the distribution of normality as required. Higher reconstruction metrics during subsequent test and deployment are thus indicative of a deviation from this normal distribution, hence indicative of an anomaly. Experimentation over established anomaly detection benchmarks and challenging real-world datasets, within the context of X-ray security screening, shows the unique promise of such a proposed approach. |
| Skip-Gram Model | A technique where by n-grams are still stored to model language, but they allow for tokens to be skipped. |
| Skipping Sampler | We introduce the Skipping Sampler, a novel algorithm to efficiently sample from the restriction of an arbitrary probability density to an arbitrary measurable set. Such conditional densities can arise in the study of risk and reliability and are often of complex nature, for example having multiple isolated modes and non-convex or disconnected support. The sampler can be seen as an instance of the Metropolis-Hastings algorithm with a particular proposal structure, and we establish sufficient conditions under which the Strong Law of Large Numbers and the Central Limit Theorem hold. We give theoretical and numerical evidence of improved performance relative to the Random Walk Metropolis algorithm. |
| Sklar’s Omega | The statistical measurement of agreement is important in a number of fields, e.g., content analysis, education, computational linguistics, biomedical imaging. We propose Sklar’s Omega, a Gaussian copula-based framework for measuring intra-coder, inter-coder, and inter-method agreement as well as agreement relative to a gold standard. We demonstrate the efficacy and advantages of our approach by applying it to both simulated and experimentally observed datasets, including data from two medical imaging studies. Application of our proposed methodology is supported by our open-source R package, sklarsomega, which is available for download from the Comprehensive R Archive Network. |
| SLAQ | Training machine learning (ML) models with large datasets can incur significant resource contention on shared clusters. This training typically involves many iterations that continually improve the quality of the model. Yet in exploratory settings, better models can be obtained faster by directing resources to jobs with the most potential for improvement. We describe SLAQ, a cluster scheduling system for approximate ML training jobs that aims to maximize the overall job quality. When allocating cluster resources, SLAQ explores the quality-runtime trade-offs across multiple jobs to maximize system-wide quality improvement. To do so, SLAQ leverages the iterative nature of ML training algorithms, by collecting quality and resource usage information from concurrent jobs, and then generating highly-tailored quality-improvement predictions for future iterations. Experiments show that SLAQ achieves an average quality improvement of up to 73% and an average delay reduction of up to 44% on a large set of ML training jobs, compared to resource fairness schedulers. |
| Slate Markov Decision Processes (slate-MDP) |
Many real-world problems come with action spaces represented as feature vectors. Although high-dimensional control is a largely unsolved problem, there has recently been progress for modest dimensionalities. Here we report on a successful attempt at addressing problems of dimensionality as high as $2000$, of a particular form. Motivated by important applications such as recommendation systems that do not fit the standard reinforcement learning frameworks, we introduce Slate Markov Decision Processes (slate-MDPs). A Slate-MDP is an MDP with a combinatorial action space consisting of slates (tuples) of primitive actions of which one is executed in an underlying MDP. The agent does not control the choice of this executed action and the action might not even be from the slate, e.g., for recommendation systems for which all recommendations can be ignored. We use deep Q-learning based on feature representations of both the state and action to learn the value of whole slates. Unlike existing methods, we optimize for both the combinatorial and sequential aspects of our tasks. The new agent’s superiority over agents that either ignore the combinatorial or sequential long-term value aspect is demonstrated on a range of environments with dynamics from a real-world recommendation system. Further, we use deep deterministic policy gradients to learn a policy that for each position of the slate, guides attention towards the part of the action space in which the value is the highest and we only evaluate actions in this area. The attention is used within a sequentially greedy procedure leveraging submodularity. Finally, we show how introducing risk-seeking can dramatically imporve the agents performance and ability to discover more far reaching strategies. |
| Slice Finder | As machine learning (ML) systems become democratized, it becomes increasingly important to help users easily debug their models. However, current data tools are still primitive when it comes to helping users trace model performance problems all the way to the data. We focus on the particular problem of slicing data to identify subsets of the validation data where the model performs poorly. This is an important problem in model validation because the overall model performance can fail to reflect that of the smaller subsets, and slicing allows users to analyze the model performance on a more granular-level. Unlike general techniques (e.g., clustering) that can find arbitrary slices, our goal is to find interpretable slices (which are easier to take action compared to arbitrary subsets) that are problematic and large. We propose Slice Finder, which is an interactive framework for identifying such slices using statistical techniques. Applications include diagnosing model fairness and fraud detection, where identifying slices that are interpretable to humans is crucial. |
| Sliced Gromov-Wasserstein (SGW) |
Recently used in various machine learning contexts, the Gromov-Wasserstein distance (GW) allows for comparing distributions that do not necessarily lie in the same metric space. However, this Optimal Transport (OT) distance requires solving a complex non convex quadratic program which is most of the time very costly both in time and memory. Contrary to GW, the Wasserstein distance (W) enjoys several properties (e.g. duality) that permit large scale optimization. Among those, the Sliced Wasserstein (SW) distance exploits the direct solution of W on the line, that only requires sorting discrete samples in 1D. This paper propose a new divergence based on GW akin to SW. We first derive a closed form for GW when dealing with 1D distributions, based on a new result for the related quadratic assignment problem. We then define a novel OT discrepancy that can deal with large scale distributions via a slicing approach and we show how it relates to the GW distance while being $O(n^2)$ to compute. We illustrate the behavior of this so called Sliced Gromov-Wasserstein (SGW) discrepancy in experiments where we demonstrate its ability to tackle similar problems as GW while being several order of magnitudes faster to compute |
| Sliced Inverse Regression (SIR) |
Sliced inverse regression (SIR) is a tool for dimension reduction in the field of multivariate statistics. In statistics, regression analysis is a popular way of studying the relationship between a response variable y and its explanatory variable x _ {\displaystyle {\underline {x}}} {\underline {x}}, which is a p-dimensional vector. There are several approaches which come under the term of regression. For example parametric methods include multiple linear regression; non-parametric techniques include local smoothing. With high-dimensional data (as p grows), the number of observations needed to use local smoothing methods escalates exponentially. Reducing the number of dimensions makes the operation computable. Dimension reduction aims to show only the most important directions of the data. SIR uses the inverse regression curve, E ( x _ | y ) {\displaystyle E({\underline {x}}\,|\,y)} E({\underline {x}}\,|\,y) to perform a weighted principal component analysis, with which one identifies the effective dimension reducing directions. Sliced Inverse Regression for Dimension Reduction |
| Sliced Recurrent Neural Network (SRNN) |
Recurrent neural networks have achieved great success in many NLP tasks. However, they have difficulty in parallelization because of the recurrent structure, so it takes much time to train RNNs. In this paper, we introduce sliced recurrent neural networks (SRNNs), which could be parallelized by slicing the sequences into many subsequences. SRNNs have the ability to obtain high-level information through multiple layers with few extra parameters. We prove that the standard RNN is a special case of the SRNN when we use linear activation functions. Without changing the recurrent units, SRNNs are 136 times as fast as standard RNNs and could be even faster when we train longer sequences. Experiments on six largescale sentiment analysis datasets show that SRNNs achieve better performance than standard RNNs. |
| Sliced Wasserstein Distance | Generative Modeling using the Sliced Wasserstein Distance |
| Sliced Wasserstein Generative Model | In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional distributions. In contrast, the sliced Wasserstein distance (SWD) factorizes high-dimensional distributions into their multiple one-dimensional marginal distributions and is thus easier to approximate. In this paper, we introduce novel approximations of the primal and dual SWD. Instead of using a large number of random projections, as it is done by conventional SWD approximation methods, we propose to approximate SWDs with a small number of parameterized orthogonal projections in an end-to-end deep learning fashion. As concrete applications of our SWD approximations, we design two types of differentiable SWD blocks to equip modern generative frameworks—Auto-Encoders (AE) and Generative Adversarial Networks (GAN). In the experiments, we not only show the superiority of the proposed generative models on standard image synthesis benchmarks, but also demonstrate the state-of-the-art performance on challenging high resolution image and video generation in an unsupervised manner. |
| Sliced-Wasserstein Autoencoder (SWAE) |
In this paper we study generative modeling via autoencoders while using the elegant geometric properties of the optimal transport (OT) problem and the Wasserstein distances. We introduce Sliced-Wasserstein Autoencoders (SWAE), which are generative models that enable one to shape the distribution of the latent space into any samplable probability distribution without the need for training an adversarial network or defining a closed-form for the distribution. In short, we regularize the autoencoder loss with the sliced-Wasserstein distance between the distribution of the encoded training samples and a predefined samplable distribution. We show that the proposed formulation has an efficient numerical solution that provides similar capabilities to Wasserstein Autoencoders (WAE) and Variational Autoencoders (VAE), while benefiting from an embarrassingly simple implementation. |
| SlicStan | Stan is a probabilistic programming language that has been increasingly used for real-world scalable projects. However, to make practical inference possible, the language sacrifices some of its usability by adopting a block syntax, which lacks compositionality and flexible user-defined functions. Moreover, the semantics of the language has been mainly given in terms of intuition about implementation, and has not been formalised. This paper provides a formal treatment of the Stan language, and introduces the probabilistic programming language SlicStan — a compositional, self-optimising version of Stan. Our main contributions are: (1) the formalisation of a core subset of Stan through an operational density-based semantics; (2) the design and semantics of the Stan-like language SlicStan, which facilities better code reuse and abstraction through its compositional syntax, more flexible functions, and information-flow type system; and (3) a formal, semantic-preserving procedure for translating SlicStan to Stan. |
| SlideNet | This work tackles the automatic fine-grained slide quality assessment problem for digitized direct smears test using the Gram staining protocol. Automatic quality assessment can provide useful information for the pathologists and the whole digital pathology workflow. For instance, if the system found a slide to have a low staining quality, it could send a request to the automatic slide preparation system to remake the slide. If the system detects severe damage in the slides, it could notify the experts that manual microscope reading may be required. In order to address the quality assessment problem, we propose a deep neural network based framework to automatically assess the slide quality in a semantic way. Specifically, the first step of our framework is to perform dense fine-grained region classification on the whole slide and calculate the region distribution histogram. Next, our framework will generate assessments of the slide quality from various perspectives: staining quality, information density, damage level and which regions are more valuable for subsequent high-magnification analysis. To make the information more accessible, we present our results in the form of a heat map and text summaries. Additionally, in order to stimulate research in this direction, we propose a novel dataset for slide quality assessment. Experiments show that the proposed framework outperforms recent related works. |
| Sliding Convolutional Attention Network (SCAN) |
Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications. State-of-the-art recurrent neural networks (RNN) based models map an input sequence to a variable length output sequence, but are usually applied in a black box manner and lack of transparency for further improvement, and the maintaining of the entire past hidden states prevents parallel computation in a sequence. In this paper, we investigate the intrinsic characteristics of text recognition, and inspired by human cognition mechanisms in reading texts, we propose a scene text recognition method with sliding convolutional attention network (SCAN). Similar to the eye movement during reading, the process of SCAN can be viewed as an alternation between saccades and visual fixations. Compared to the previous recurrent models, computations over all elements of SCAN can be fully parallelized during training. Experimental results on several challenging benchmarks, including the IIIT5k, SVT and ICDAR 2003/2013 datasets, demonstrate the superiority of SCAN over state-of-the-art methods in terms of both the model interpretability and performance. |
| Sliding Line Point Regression (SLPR) |
Traditional text detection methods mostly focus on quadrangle text. In this study we propose a novel method named sliding line point regression (SLPR) in order to detect arbitrary-shape text in natural scene. SLPR regresses multiple points on the edge of text line and then utilizes these points to sketch the outlines of the text. The proposed SLPR can be adapted to many object detection architectures such as Faster R-CNN and R-FCN. Specifically, we first generate the smallest rectangular box including the text with region proposal network (RPN), then isometrically regress the points on the edge of text by using the vertically and horizontally sliding lines. To make full use of information and reduce redundancy, we calculate x-coordinate or y-coordinate of target point by the rectangular box position, and just regress the remaining y-coordinate or x-coordinate. Accordingly we can not only reduce the parameters of system, but also restrain the points which will generate more regular polygon. Our approach achieved competitive results on traditional ICDAR2015 Incidental Scene Text benchmark and curve text detection dataset CTW1500. |
| Sliding Suffix Tree | We consider a sliding window over a stream of characters from some finite alphabet. The user wants to perform deterministic substring matching on the current sliding window content and obtain positions of the matches. We present an indexed version of the sliding window based on a suffix tree. The data structure has optimal time queries $\Theta(m+occ)$ and amortized constant time updates, where $m$ is the length of the query string and $occ$ the number of occurrences. |
| Sliding Window Discrete Fourier Transform (SWDFT) |
This paper introduces a new tool for time-series analysis: the Sliding Window Discrete Fourier Transform (SWDFT). The SWDFT is especially useful for time-series with local- in-time periodic components. We define a 5-parameter model for noiseless local periodic signals, then study the SWDFT of this model. Our study illustrates several key concepts crucial to analyzing time-series with the SWDFT, in particular Aliasing, Leakage, and Ringing. We also show how these ideas extend to R > 1 local periodic components, using the linearity property of the Fourier transform. Next, we propose a simple procedure for estimating the 5 parameters of our local periodic signal model using the SWDFT. Our estimation procedure speeds up computation by using a trigonometric identity that linearizes estimation of 2 of the 5 parameters. We conclude with a very small Monte Carlo simulation study of our estimation procedure under different levels of noise. swdft |
| SLIM | Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, and global explanations. One of the main challenges in interpretability is designing explanation systems that can capture aspects of each of these explanation types, in order to develop a more thorough understanding of the model. We address this challenge in a novel model called SLIM that uses local linear modeling techniques along with a dual interpretation of random forests (both as a supervised neighborhood approach and as a feature selection method). SLIM has two fundamental advantages over existing interpretability systems. First, while it is effective as a black-box explanation system, SLIM itself is a highly accurate predictive model that provides faithful self explanations, and thus sidesteps the typical accuracy-interpretability trade-off. Second, SLIM provides both example- based and local explanations and can detect global patterns, which allows it to diagnose limitations in its local explanations. |
| SLIM LSTM | Long Short-Term Memory (LSTM) Recurrent Neural networks (RNNs) rely on gating signals, each driven by a function of a weighted sum of at least 3 components: (i) one of an adaptive weight matrix multiplied by the incoming external input vector sequence, (ii) one adaptive weight matrix multiplied by the previous memory/state vector, and (iii) one adaptive bias vector. In effect, they augment the simple Recurrent Neural Networks (sRNNs) structure with the addition of a ‘memory cell’ and the incorporation of at most 3 gating signals. The standard LSTM structure and components encompass redundancy and overly increased parameterization. In this paper, we systemically introduce variants of the LSTM RNNs, referred to as SLIM LSTMs. These variants express aggressively reduced parameterizations to achieve computational saving and/or speedup in (training) performance—while necessarily retaining (validation accuracy) performance comparable to the standard LSTM RNN. |
| Slimmable Network | ➘ “Slimmable Neural Network” |
| Slimmable Neural Network | We present a simple and general method to train a single neural network executable at different widths (number of channels in a layer), permitting instant and adaptive accuracy-efficiency trade-offs at runtime. Instead of training individual networks with different width configurations, we train a shared network with switchable batch normalization. At runtime, the network can adjust its width on the fly according to on-device benchmarks and resource constraints, rather than downloading and offloading different models. Our trained networks, named slimmable neural networks, achieve similar (and in many cases better) ImageNet classification accuracy than individually trained models of MobileNet v1, MobileNet v2, ShuffleNet and ResNet-50 at different widths respectively. We also demonstrate better performance of slimmable models compared with individual ones across a wide range of applications including COCO bounding-box object detection, instance segmentation and person keypoint detection without tuning hyper-parameters. Lastly we visualize and discuss the learned features of slimmable networks. Code and models are available at: https://…/slimmable_networks |
| SlimNet | Deep neural networks have achieved increasingly accurate results on a wide variety of complex tasks. However, much of this improvement is due to the growing use and availability of computational resources (e.g use of GPUs, more layers, more parameters, etc). Most state-of-the-art deep networks, despite performing well, over-parameterize approximate functions and take a significant amount of time to train. With increased focus on deploying deep neural networks on resource constrained devices like smart phones, there has been a push to evaluate why these models are so resource hungry and how they can be made more efficient. This work evaluates and compares three distinct methods for deep model compression and acceleration: weight pruning, low rank factorization, and knowledge distillation. Comparisons on VGG nets trained on CIFAR10 show that each of the models on their own are effective, but that the true power lies in combining them. We show that by combining pruning and knowledge distillation methods we can create a compressed network 85 times smaller than the original, all while retaining 96% of the original model’s accuracy. |
| SLING | SLING, an experimental system for parsing natural language text directly into a representation of its meaning as a semantic frame graph. The output frame graph directly captures the semantic annotations of interest to the user, while avoiding the pitfalls of pipelined systems by not running any intermediate stages, additionally preventing unnecessary computation. SLING uses a special-purpose recurrent neural network model to compute the output representation of input text through incremental editing operations on the frame graph. The frame graph, in turn, is flexible enough to capture many semantic tasks of interest (more on this below). SLING’s parser is trained using only the input words, bypassing the need for producing any intermediate annotations (e.g. dependency parses). |
| Slopegraphs | An overview of Edward Tufte’s “slopegraphs”; their history; good and bad examples; when to use slopegraphs; slopegraph best practices. (from Charlie Park) |
| Slow Feature Analysis (SFA) |
Slow feature analysis (SFA) is an unsupervised learning algorithm for extracting slowly varying features from a quickly varying input signal. It has been successfully applied, e.g., to the self-organization of complex-cell receptive fields, the recognition of whole objects invariant to spatial transformations, the self-organization of place-cells, extraction of driving forces, and to nonlinear blind source separation. Theoretical Analysis of the Optimal Free Responses of Graph-Based SFA for the Design of Training Graphs A quick introduction to Slow Feature Analysis Slow Feature Analysis: Unsupervised Learning of Invariances |
| Slow Intelligence System (SIS) |
In this talk I will introduce the concept of slow intelligence. Not all intelligent systems have fast intelligence. There are a surprisingly large number of intelligent systems, quasi-intelligent systems and semi-intelligent systems that have slow intelligence. Such slow intelligence systems are often neglected in mainstream research on intelligent systems, but they are really worthy of our attention and emulation. I will discuss the general characteristics of slow intelligence systems and then concentrate on evolutionary query processing for distributed multimedia systems as an example of artificial slow intelligence systems. |
| Sluice Networks | Multi-task learning is partly motivated by the observation that humans bring to bear what they know about related problems when solving new ones. Similarly, deep neural networks can profit from related tasks by sharing parameters with other networks. However, humans do not consciously decide to transfer knowledge between tasks (and are typically not aware of the transfer). In machine learning, it is hard to estimate if sharing will lead to improvements; especially if tasks are only loosely related. To overcome this, we introduce Sluice Networks, a general framework for multi-task learning where trainable parameters control the amount of sharing — including which parts of the models to share. Our framework goes beyond and generalizes over previous proposals in enabling hard or soft sharing of all combinations of subspaces, layers, and skip connections. We perform experiments on three task pairs from natural language processing, and across seven different domains, using data from OntoNotes 5.0, and achieve up to 15% average error reductions over common approaches to multi-task learning. We analyze when the architecture is particularly helpful, as well as its ability to fit noise. We show that a) label entropy is predictive of gains in sluice networks, confirming findings for hard parameter sharing, and b) while sluice networks easily fit noise, they are robust across domains in practice. |
| Small Area Estimation (SAE) |
Small area estimation is any of several statistical techniques involving the estimation of parameters for small sub-populations, generally used when the sub-population of interest is included in a larger survey. The term ‘small area’ in this context generally refers to a small geographical area such as a county. It may also refer to a ‘small domain’, i.e. a particular demographic within an area. If a survey has been carried out for the population as a whole (for example, a nation or state-wide survey), the sample size within any particular small area may be too small to generate accurate estimates from the data. To deal with this problem, it may be possible to use additional data (such as census records) that exists for these small areas in order to obtain estimates. http://…-area-estimation-101-old-materials-posted saeSim,sae2,sae |
| Small Sample Learning (SSL) |
As a promising area in artificial intelligence, a new learning paradigm, called Small Sample Learning (SSL), has been attracting prominent research attention in the recent years. In this paper, we aim to present a survey to comprehensively introduce the current techniques proposed on this topic. Specifically, current SSL techniques can be mainly divided into two categories. The first category of SSL approaches can be called ‘concept learning’, which emphasizes learning new concepts from only few related observations. The purpose is mainly to simulate human learning behaviors like recognition, generation, imagination, synthesis and analysis. The second category is called ‘experience learning’, which usually co-exists with the large sample learning manner of conventional machine learning. This category mainly focuses on learning with insufficient samples, and can also be called small data learning in some literatures. More extensive surveys on both categories of SSL techniques are introduced and some neuroscience evidences are provided to clarify the rationality of the entire SSL regime, and the relationship with human learning process. Some discussions on the main challenges and possible future research directions along this line are also presented. |
| Smallify | As neural networks become widely deployed in different applications and on different hardware, it has become increasingly important to optimize inference time and model size along with model accuracy. Most current techniques optimize model size, model accuracy and inference time in different stages, resulting in suboptimal results and computational inefficiency. In this work, we propose a new technique called Smallify that optimizes all three of these metrics at the same time. Specifically we present a new method to simultaneously optimize network size and model performance by neuron-level pruning during training. Neuron-level pruning not only produces much smaller networks but also produces dense weight matrices that are amenable to efficient inference. By applying our technique to convolutional as well as fully connected models, we show that Smallify can reduce network size by 35X with a 6X improvement in inference time with similar accuracy as models found by traditional training techniques. |
| SMART | SMART is an open source web application designed to help data scientists and research teams efficiently build labeled training data sets for supervised machine learning tasks. SMART provides users with an intuitive interface for creating labeled data sets, supports active learning to help reduce the required amount of labeled data, and incorporates inter-rater reliability statistics to provide insight into label quality. SMART is designed to be platform agnostic and easily deployable to meet the needs of as many different research teams as possible. The project website contains links to the code repository and extensive user documentation. |
| Smart Contract | A smart contract is a computer protocol intended to digitally facilitate, verify, or enforce the negotiation or performance of a contract. Smart contracts allow the performance of credible transactions without third parties. These transactions are trackable and irreversible. Proponents of smart contracts claim that many kinds of contractual clauses may be made partially or fully self-executing, self-enforcing, or both. The aim of smart contracts is to provide security that is superior to traditional contract law and to reduce other transaction costs associated with contracting. Various cryptocurrencies have implemented types of smart contracts. |
| Smart Data | |
| Smart Mining for Deep Metric Learning | To solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance between samples from different classes. Though successful, the training convergence of this triplet model can be compromised by the fact that the vast majority of the training samples will produce gradients with magnitudes that are close to zero. This issue has motivated the development of methods that explore the global structure of the embedding and other methods that explore hard negative/positive mining. The effectiveness of such mining methods is often associated with intractable computational requirements. In this paper, we propose a novel deep metric learning method that combines the triplet model and the global structure of the embedding space. We rely on a smart mining procedure that produces effective training samples for a low computational cost. In addition, we propose an adaptive controller that automatically adjusts the smart mining hyper-parameters and speeds up the convergence of the training process. We show empirically that our proposed method allows for fast and more accurate training of triplet ConvNets than other competing mining methods. Additionally, we show that our method achieves new state-of-the-art embedding results for CUB-200-2011 and Cars196 datasets. |
| Smart ‘Predict, then Optimize’ (SPO) |
Many real-world analytics problems involve two significant challenges: prediction and optimization. Due to the typically complex nature of each challenge, the standard paradigm is to predict, then optimize. By and large, machine learning tools are intended to minimize prediction error and do not account for how the predictions will be used in a downstream optimization problem. In contrast, we propose a new and very general framework, called Smart ‘Predict, then Optimize’ (SPO), which directly leverages the optimization problem structure, i.e., its objective and constraints, for designing successful analytics tools. A key component of our framework is the SPO loss function, which measures the quality of a prediction by comparing the objective values of the solutions generated using the predicted and observed parameters, respectively. Training a model with respect to the SPO loss is computationally challenging, and therefore we also develop a surrogate loss function, called the SPO+ loss, which upper bounds the SPO loss, has desirable convexity properties, and is statistically consistent under mild conditions. We also propose a stochastic gradient descent algorithm which allows for situations in which the number of training samples is large, model regularization is desired, and/or the optimization problem of interest is nonlinear or integer. Finally, we perform computational experiments to empirically verify the success of our SPO framework in comparison to the standard predict-then-optimize approach. |
| Smart System | Smart systems incorporate functions of sensing, actuation, and control in order to describe and analyze a situation, and make decisions based on the available data in a predictive or adaptive manner, thereby performing smart actions. In most cases the ‘smartness’ of the system can be attributed to autonomous operation based on closed loop control, energy efficiency, and networking capabilities. |
| Smart Web Services (SmartWS) |
The past few years have been marked by an increased use of sensor technologies, abundant availability of mobile devices, and growing popularity of wearables, which enable the direct integration of their data as part of rich client applications. Despite the potential and added value that such aggregate applications bring, the implementations are usually custom solutions for particular use cases and do not support easy integration of further devices. To this end, the vision of the Web of Things (WoT) is to leverage Web standards in order to interconnect all types of devices and real-world objects, and thus to make them a part of the World Wide Web (WWW) and provide overall interoperability. In this context we introduce Smart Web Services (SmartWS) that not only provide remote access to resources and functionalities, by relying on standard communication protocols, but also encapsulate `intelligence’. Smartness features can include, for instance, context-based adaptation, cognition, inference and rules that implement autonomous decision logic in order to realize services that automatically perform tasks on behalf of the users, without requiring their explicit involvement. In this paper, we present the key characteristics of SmartWS, and introduce a reference implementation framework. Furthermore, we describe a specific use case for implementing SmartWS in the medical domain and specify a maturity model for determining the quality and usability of SmartWS. |
| SMarTplan | Smart factories are on the verge of becoming the new industrial paradigm, wherein optimization permeates all aspects of production, from concept generation to sales. To fully pursue this paradigm, flexibility in the production means as well as in their timely organization is of paramount importance. AI is planning a major role in this transition, but the scenarios encountered in practice might be challenging for current tools. Task planning is one example where AI enables more efficient and flexible operation through an online automated adaptation and rescheduling of the activities to cope with new operational constraints and demands. In this paper we present SMarTplan, a task planner specifically conceived to deal with real-world scenarios in the emerging smart factory paradigm. Including both special-purpose and general-purpose algorithms, SMarTplan is based on current automated reasoning technology and it is designed to tackle complex application domains. In particular, we show its effectiveness on a logistic scenario, by comparing its specialized version with the general purpose one, and extending the comparison to other state-of-the-art task planners. |
| SmartTable | We introduce SmartTable, an online spreadsheet application that is equipped with intelligent assistance capabilities. With a focus on relational tables, describing entities along with their attributes, we offer assistance in two flavors: (i) for populating the table with additional entities (rows) and (ii) for extending it with additional entity attributes (columns). We provide details of our implementation, which is also released as open source. The application is available at http://smarttable.cc. |
| Smirnov Tree | We introduce a generalization of Smirnov words in the context of labeled binary trees, which we call Smirnov trees. We study the generating function for ascent-descent statistics on Smirnov trees and establish that it is $e$-positive, which is akin to the classical case of Smirnov words. Our proof relies on an intricate weight-preserving bijection. |
| Smooth Additive Quantile Regression Model | qgam |
| Smooth Density Spatial Quantile Regression | We derive the properties and demonstrate the desirability of a model-based method for estimating the spatially-varying effects of covariates on the quantile function. By modeling the quantile function as a combination of I-spline basis functions and Pareto tail distributions, we allow for flexible parametric modeling of the extremes while preserving non-parametric flexibility in the center of the distribution. We further establish that the model guarantees the desired degree of differentiability in the density function and enables the estimation of non-stationary covariance functions dependent on the predictors. We demonstrate through a simulation study that the proposed method produces more efficient estimates of the effects of predictors than other methods, particularly in distributions with heavy tails. To illustrate the utility of the model we apply it to measurements of benzene collected around an oil refinery to determine the effect of an emission source within the refinery on the distribution of the fence line measurements. |
| Smooth Imitation Learning (SIL) |
In Smooth Imitation Learning for online sequence prediction is the goal is to train a policy that can smoothly imitate demonstrated behavior in a dynamic and continuous environment in response to online, sequential context input. |
| Smooth Neighbors on Teacher Graph (SNTG) |
The paper proposes an inductive semi-supervised learning method, called Smooth Neighbors on Teacher Graphs (SNTG). At each iteration during training, a graph is dynamically constructed based on predictions of the teacher model, i.e., the implicit self-ensemble of models. Then the graph serves as a similarity measure with respect to which the representations of ‘similar’ neighboring points are learned to be smooth on the low dimensional manifold. We achieve state-of-the-art results on semi-supervised learning benchmarks. The error rates are 9.89%, 3.99% for CIFAR-10 with 4000 labels, SVHN with 500 labels, respectively. In particular, the improvements are significant when the labels are scarce. For non-augmented MNIST with only 20 labels, the error rate is reduced from previous 4.81% to 1.36%. Our method is also effective under noisy supervision and shows robustness to incorrect labels. |
| Smoothly Clipped Absolute Deviation (SCAD) |
Variable selection is fundamental to high-dimensional statistical modeling, including nonparametric regression. Many approaches in use are stepwise selection procedures, which can be computationally expensive and ignore stochastic errors in the variable selection process. In this article, penalized likelihood approaches are proposed to handle these kinds of problems. The proposed methods select variables and estimate coefficients simultaneously. Hence they enable us to construct confidence intervals for estimated parameters. The proposed approaches are distinguished from others in that the penalty functions are symmetric, nonconcave on (0,inf), and have singularities at the origin to produce sparse solutions. Furthermore, the penalty functions should be bounded by a constant to reduce bias and satisfy certain conditions to yield continuous solutions. A new algorithm is proposed for optimizing penalized likelihood functions. http://…/SCAD_Documentation.pdf |
| SMTM | Manually labeling documents is tedious and expensive, but it is essential for training a traditional text classifier. In recent years, a few dataless text classification techniques have been proposed to address this problem. However, existing works mainly center on single-label classification problems, that is, each document is restricted to belonging to a single category. In this paper, we propose a novel Seed-guided Multi-label Topic Model, named SMTM. With a few seed words relevant to each category, SMTM conducts multi-label classification for a collection of documents without any labeled document. In SMTM, each category is associated with a single category-topic which covers the meaning of the category. To accommodate with multi-labeled documents, we explicitly model the category sparsity in SMTM by using spike and slab prior and weak smoothing prior. That is, without using any threshold tuning, SMTM automatically selects the relevant categories for each document. To incorporate the supervision of the seed words, we propose a seed-guided biased GPU (i.e., generalized Polya urn) sampling procedure to guide the topic inference of SMTM. Experiments on two public datasets show that SMTM achieves better classification accuracy than state-of-the-art alternatives and even outperforms supervised solutions in some scenarios. |
| SMuRF | Within the statistical and machine learning literature, regularization techniques are often used to construct sparse (predictive) models. Most regularization strategies only work for data where all predictors are of the same type, such as Lasso regression for continuous predictors. However, many predictive problems involve different predictor types. We propose a multi-type Lasso penalty that acts on the objective function as a sum of subpenalties, one for each predictor type. As such, we perform predictor selection and level fusion within a predictor in a data-driven way, simultaneous with the parameter estimation process. We develop a new estimation strategy for convex predictive models with this multi-type penalty. Using the theory of proximal operators, our estimation procedure is computationally efficient, partitioning the overall optimization problem into easier to solve subproblems, specific for each predictor type and its associated penalty. The proposed SMuRF algorithm improves on existing solvers in both accuracy and computational efficiency. This is demonstrated with an extensive simulation study and the analysis of a case-study on insurance pricing analytics. |
| SMURFF | Bayesian Matrix Factorization (BMF) is a powerful technique for recommender systems because it produces good results and is relatively robust against overfitting. Yet BMF is more computationally intensive and thus more challenging to implement for large datasets. In this work we present SMURFF a high-performance feature-rich framework to compose and construct different Bayesian matrix-factorization methods. The framework has been successfully used in to do large scale runs of compound-activity prediction. SMURFF is available as open-source and can be used both on a supercomputer and on a desktop or laptop machine. Documentation and several examples are provided as Jupyter notebooks using SMURFF’s high-level Python API. |
| Snake | A regularized optimization problem over a large unstructured graph is studied, where the regularization term is tied to the graph geometry. Typical regularization examples include the total variation and the Laplacian regularizations over the graph. When applying the proximal gradient algorithm to solve this problem, there exist quite affordable methods to implement the proximity operator (backward step) in the special case where the graph is a simple path without loops. In this paper, an algorithm, referred to as ‘Snake’, is proposed to solve such regularized problems over general graphs, by taking benefit of these fast methods. The algorithm consists in properly selecting random simple paths in the graph and performing the proximal gradient algorithm over these simple paths. This algorithm is an instance of a new general stochastic proximal gradient algorithm, whose convergence is proven. Applications to trend filtering and graph inpainting are provided among others. Numerical experiments are conducted over large graphs. |
| Snap Machine Learning (Snap ML) |
We describe an efficient, scalable machine learning library that enables very fast training of generalized linear models. We demonstrate that our library can remove the training time as a bottleneck for machine learning workloads, opening the door to a range of new applications. For instance, it allows more agile development, faster and more fine-grained exploration of the hyper-parameter space, enables scaling to massive datasets and makes frequent re-training of models possible in order to adapt to events as they occur. Our library, named Snap Machine Learning (Snap ML), combines recent advances in machine learning systems and algorithms in a nested manner to reflect the hierarchical architecture of modern distributed systems. This allows us to effectively leverage available network, memory and heterogeneous compute resources. On a terabyte-scale publicly available dataset for click-through-rate prediction in computational advertising, we demonstrate the training of a logistic regression classifier in 1.53 minutes, a 46x improvement over the fastest reported performance. |
| Snapshot Distillation | Optimizing a deep neural network is a fundamental task in computer vision, yet direct training methods often suffer from over-fitting. Teacher-student optimization aims at providing complementary cues from a model trained previously, but these approaches are often considerably slow due to the pipeline of training a few generations in sequence, i.e., time complexity is increased by several times. This paper presents snapshot distillation (SD), the first framework which enables teacher-student optimization in one generation. The idea of SD is very simple: instead of borrowing supervision signals from previous generations, we extract such information from earlier epochs in the same generation, meanwhile make sure that the difference between teacher and student is sufficiently large so as to prevent under-fitting. To achieve this goal, we implement SD in a cyclic learning rate policy, in which the last snapshot of each cycle is used as the teacher for all iterations in the next cycle, and the teacher signal is smoothed to provide richer information. In standard image classification benchmarks such as CIFAR100 and ILSVRC2012, SD achieves consistent accuracy gain without heavy computational overheads. We also verify that models pre-trained with SD transfers well to object detection and semantic segmentation in the PascalVOC dataset. |
| Snapshot Ensembles | Ensembles of neural networks are known to be much more robust and accurate than individual networks. However, training multiple deep networks for model averaging is computationally expensive. In this paper, we propose a method to obtain the seemingly contradictory goal of ensembling multiple neural networks at no additional training cost. We achieve this goal by training a single neural network, converging to several local minima along its optimization path and saving the model parameters. To obtain repeated rapid convergence, we leverage recent work on cyclic learning rate schedules. The resulting technique, which we refer to as Snapshot Ensembling, is simple, yet surprisingly effective. We show in a series of experiments that our approach is compatible with diverse network architectures and learning tasks. It consistently yields lower error rates than state-of-the-art single models at no additional training cost, and compares favorably with traditional network ensembles. On CIFAR-10 and CIFAR-100 our DenseNet Snapshot Ensembles obtain error rates of 3.4% and 17.4% respectively. Snapshot Ensembles in Keras |
| SneakPeek | Nowadays, eye tracking is the most used technology to detect areas of interest. This kind of technology requires specialized equipment recording user’s eyes. In this paper, we propose SneakPeek, a different approach to detect areas of interest on images displayed in web pages based on the zooming and panning actions of the users through the image. We have validated our proposed solution with a group of test subjects that have performed a test in our on-line prototype. Being this the first iteration of the algorithm, we have found both good and bad results, depending on the type of image. In specific, SneakPeek works best with medium/big objects in medium/big sized images. The reason behind it is the limitation on detection when smartphone screens keep getting bigger and bigger. SneakPeek can be adapted to any website by simply adapting the controller interface for the specific case. |
| SNIPER | We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visual recognition tasks. Instead of processing every pixel in an image pyramid, SNIPER processes context regions around ground-truth instances (referred to as chips) at the appropriate scale. For background sampling, these context-regions are generated using proposals extracted from a region proposal network trained with a short learning schedule. Hence, the number of chips generated per image during training adaptively changes based on the scene complexity. SNIPER only processes 30% more pixels compared to the commonly used single scale training at 800×1333 pixels on the COCO dataset. But, it also observes samples from extreme resolutions of the image pyramid, like 1400×2000 pixels. As SNIPER operates on resampled low resolution chips (512×512 pixels), it can have a batch size as large as 20 on a single GPU even with a ResNet-101 backbone. Therefore it can benefit from batch-normalization during training without the need for synchronizing batch-normalization statistics across GPUs. SNIPER brings training of instance level recognition tasks like object detection closer to the protocol for image classification and suggests that the commonly accepted guideline that it is important to train on high resolution images for instance level visual recognition tasks might not be correct. Our implementation based on Faster-RCNN with a ResNet-101 backbone obtains an mAP of 47.6% on the COCO dataset for bounding box detection and can process 5 images per second with a single GPU. |
| Snoogle | Embedding small devices into everyday objects like toasters and coffee mugs creates a wireless network of objects. These embedded devices can contain a description of the underlying objects, or other user defined information. In this paper, we present Snoogle, a search engine for such a network. A user can query Snoogle to find a particular mobile object, or a list of objects that fit the description. Snoogle uses information retrieval techniques to index information and process user queries, and Bloom filters to reduce communication overhead. Security and privacy protections are also engineered into Snoogle to protect sensitive information. We have implemented a prototype of Snoogle using off-the-shelf sensor motes, and conducted extensive experiments to evaluate the system performance. |
| Snoogle | Snoogle is a graphical, SWRL-based ontology mapper to assist in the task of OWL ontology alignment. It allows users to visualize ontologies and then draw mappings from one to another on a graphical canvas. Users draw mappings as they see them in their head, and then Snoogle turns these mappings into SWRL/RDF or SWRL/XML for use in a knowledge base. |
| Snorkel | Today’s state-of-the-art machine learning models require massive labeled training sets–which usually do not exist for real-world applications. Instead, Snorkel is based around the new data programming paradigm, in which the developer focuses on writing a set of labeling functions, which are just scripts that programmatically label data. The resulting labels are noisy, but Snorkel automatically models this process – learning, essentially, which labeling functions are more accurate than others – and then uses this to train an end model (for example, a deep neural network in TensorFlow). |
| Snowdoop | Hadoop made it convenient to process data in very large distributed databases, and also convenient to create them, using the Hadoop Distributed File System. But eventually word got out that Hadoop is slow, and very limited in available data operations. Both of those shortcomings are addressed to a large extent by the new kid on the block, Spark. Spark is apparently much faster than Hadoop, sometimes dramatically so, due to strong caching ability and a wider variety of available operations. But even Spark su ers a very practical problem, shared by the others mentioned above: All of these systems are complicated. There is a considerable amount of con guration to do, worsened by dependence on infrastructure software such as Java or MPI, and in some cases by interface software such as rJava. Some of this requires systems knowledge that many R users may lack. And once they do get these systems set up, they may be required to design algorithms with world views quite different from R, even though technically they are coding in R. So, do we really need all that complicated machinery? Hadoop and Spark provide e cient dis- tributed sort operations, but if one’s application does not depend on sorting, we have a cost-bene t issue here. Here is an alternative, more of a general approach rather than a package, which I call ‘Snowdoop.’ (The name alludes to the fact that it uses the section of the parallel package derived from the old snow package.) The idea is to retain the notion of chunking les into distributed mini-files, but (a) do this on one’s own, and (b) the process those les using ordinary R code, not fancy new functions like Hadoop and Spark require. https://…pdate-on-snowdoop-a-mapreduce-alternative |
| SoaAlloc | We propose SoaAlloc, a dynamic object allocator for Single-Method Multiple-Objects applications in CUDA. SoaAlloc is the first allocator for GPUs that (a) arranges allocations in a SIMD-friendly Structure of Arrays (SOA) data layout, (b) provides a do-all operation for maximizing the benefit of SOA, and (c) is on par with state-of-the-art memory allocators for raw (de)allocation time. Our benchmarks show that the SOA layout leads to significantly better memory bandwidth utilization, resulting in a 2x speedup of application code. |
| Sobel Operator | The Sobel operator, sometimes called Sobel Filter, is used in image processing and computer vision, particularly within edge detection algorithms, and creates an image which emphasizes edges and transitions. It is named after Irwin Sobel, who presented the idea of an ‘Isotropic 3×3 Image Gradient Operator’ at a talk at the Stanford Artificial Intelligence Project (SAIP) in 1968. Technically, it is a discrete differentiation operator, computing an approximation of the gradient of the image intensity function. At each point in the image, the result of the Sobel operator is either the corresponding gradient vector or the norm of this vector. The Sobel operator is based on convolving the image with a small, separable, and integer valued filter in horizontal and vertical direction and is therefore relatively inexpensive in terms of computations. On the other hand, the gradient approximation that it produces is relatively crude, in particular for high frequency variations in the image. The Kayyali operator for edge detection is another operator generated from Sobel operator. |
| Sobol Indices | Sobol indices are a widespread quantitative measure for variance-based global sensitivity analysis, but computing and utilizing them remains challenging for high-dimensional systems. |
| Sobolev GAN | ➘ “Sobolev Integral Probability Metric” |
| Sobolev Integral Probability Metric (IPM) |
We propose a new Integral Probability Metric (IPM) between distributions: the Sobolev IPM. The Sobolev IPM compares the mean discrepancy of two distributions for functions (critic) restricted to a Sobolev ball defined with respect to a dominant measure $\mu$. We show that the Sobolev IPM compares two distributions in high dimensions based on weighted conditional Cumulative Distribution Functions (CDF) of each coordinate on a leave one out basis. The Dominant measure $\mu$ plays a crucial role as it defines the support on which conditional CDFs are compared. Sobolev IPM can be seen as an extension of the one dimensional Von-Mises Cram\’er statistics to high dimensional distributions. We show how Sobolev IPM can be used to train Generative Adversarial Networks (GANs). We then exploit the intrinsic conditioning implied by Sobolev IPM in text generation. Finally we show that a variant of Sobolev GAN achieves competitive results in semi-supervised learning on CIFAR-10, thanks to the smoothness enforced on the critic by Sobolev GAN which relates to Laplacian regularization. |
| Sobolev Training | At the heart of deep learning we aim to use neural networks as function approximators – training them to produce outputs from inputs in emulation of a ground truth function or data creation process. In many cases we only have access to input-output pairs from the ground truth, however it is becoming more common to have access to derivatives of the target output with respect to the input – for example when the ground truth function is itself a neural network such as in network compression or distillation. Generally these target derivatives are not computed, or are ignored. This paper introduces Sobolev Training for neural networks, which is a method for incorporating these target derivatives in addition the to target values while training. By optimising neural networks to not only approximate the function’s outputs but also the function’s derivatives we encode additional information about the target function within the parameters of the neural network. Thereby we can improve the quality of our predictors, as well as the data-efficiency and generalization capabilities of our learned function approximation. We provide theoretical justifications for such an approach as well as examples of empirical evidence on three distinct domains: regression on classical optimisation datasets, distilling policies of an agent playing Atari, and on large-scale applications of synthetic gradients. In all three domains the use of Sobolev Training, employing target derivatives in addition to target values, results in models with higher accuracy and stronger generalisation. |
| Social Influence Maximization Problem (SIM Problem) |
➘ “Target Set Selection in a Social Network” |
| Social Network Analysis (SNA) |
Social network analysis (SNA) is a strategy for investigating social structures through the use of network and graph theories. It characterizes networked structures in terms of nodes (individual actors, people, or things within the network) and the ties or edges (relationships or interactions) that connect them. Examples of social structures commonly visualized through social network analysis include social media networks, friendship and acquaintance networks, kinship, disease transmission,and sexual relationships. These networks are often visualized through sociograms in which nodes are represented as points and ties are represented as lines. Social network analysis has emerged as a key technique in modern sociology. It has also gained a significant following in anthropology, biology, communication studies, economics, geography, history, information science, organizational studies, political science, social psychology, development studies, and sociolinguistics and is now commonly available as a consumer tool. |
| Social Physics (SocioPhysics) |
Social physics or sociophysics is a field of science which uses mathematical tools inspired by physics to understand the behavior of human crowds. In a modern commercial use, it can also refer to the analysis of social phenomena with big data. Social physics is closely related to econophysics which uses physics methods to describe economics. https://www.datasciencecentral.com/profiles/blogs/the-upcoming-revolution-in-predictive-analytics-and-data-science |
| Social Relationship Graph Generation Network (SRG-GN) |
Socially-intelligent agents are of growing interest in artificial intelligence. To this end, we need systems that can understand social relationships in diverse social contexts. Inferring the social context in a given visual scene not only involves recognizing objects, but also demands a more in-depth understanding of the relationships and attributes of the people involved. To achieve this, one computational approach for representing human relationships and attributes is to use an explicit knowledge graph, which allows for high-level reasoning. We introduce a novel end-to-end-trainable neural network that is capable of generating a Social Relationship Graph – a structured, unified representation of social relationships and attributes – from a given input image. Our Social Relationship Graph Generation Network (SRG-GN) is the first to use memory cells like Gated Recurrent Units (GRUs) to iteratively update the social relationship states in a graph using scene and attribute context. The neural network exploits the recurrent connections among the GRUs to implement message passing between nodes and edges in the graph, and results in significant improvement over previous methods for social relationship recognition. |
| Social Wi-Fi | Many retailers offer Wi-Fi to attract and retain customers. Now some retailers hope to get more from wireless networking via Social Wi-Fi, in which customers get free connectivity by logging in to the retailer’s network using their credentials from a social network account, such as Facebook. The user gets free wireless connectivity. The retailer gets access to customer data for marketing purposes. For example, the retailer could use the data to tailor offers to the customer, such as an in-store coupon for a favorite brand. |
| SocialGCN | Collaborative Filtering (CF) is one of the most successful approaches for recommender systems. With the emergence of online social networks, social recommendation has become a popular research direction. Most of these social recommendation models utilized each user’s local neighbors’ preferences to alleviate the data sparsity issue in CF. However, they only considered the local neighbors of each user and neglected the process that users’ preferences are influenced as information diffuses in the social network. Recently, Graph Convolutional Networks~(GCN) have shown promising results by modeling the information diffusion process in graphs that leverage both graph structure and node feature information. To this end, in this paper, we propose an effective graph convolutional neural network based model for social recommendation. Based on a classical CF model, the key idea of our proposed model is that we borrow the strengths of GCNs to capture how users’ preferences are influenced by the social diffusion process in social networks. The diffusion of users’ preferences is built on a layer-wise diffusion manner, with the initial user embedding as a function of the current user’s features and a free base user latent vector that is not contained in the user feature. Similarly, each item’s latent vector is also a combination of the item’s free latent vector, as well as its feature representation. Furthermore, we show that our proposed model is flexible when user and item features are not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model. |
| Socially Aware Kalman Neural Network (SAKNN) |
Trajectory prediction is a critical technique in the navigation of robots and autonomous vehicles. However, the complex traffic and dynamic uncertainties yield challenges in the effectiveness and robustness in modeling. We purpose a data-driven approach socially aware Kalman neural networks (SAKNN) where the interaction layer and the Kalman layer are embedded in the architecture, resulting in a class of architectures with huge potential to directly learn from high variance sensor input and robustly generate low variance outcomes. The evaluation of our approach on NGSIM dataset demonstrates that SAKNN performs state-of-the-art on prediction effectiveness in a relatively long-term horizon and significantly improves the signal-to-noise ratio of the predicted signal. |
| Social-Relation based Centrality (SoReC) |
Mobile Social Networks (MSNs) have been evolving and enabling various fields in recent years. Recent advances in mobile edge computing, caching, and device-to-device communications, can have significant impacts on 5G systems. In those settings, identifying central users is crucial. It can provide important insights into designing and deploying diverse services and applications. However, it is challenging to evaluate the centrality of nodes in MSNs with dynamic environments. In this paper, we propose a Social-Relation based Centrality (SoReC) measure, in which social network information is used to quantify the influence of each user in MSNs. We first introduce a new metric to estimate direct social relations among users via direct contacts, and then extend the metric to explore indirect social relations among users bridging by the third parties. Based on direct and indirect social relations, we detect the influence spheres of users and quantify their influence in the networks. Simulations on real-world networks show that the proposed measure can perform well in identifying future influential users in MSNs. |
| Sockeye | We describe Sockeye (version 1.12), an open-source sequence-to-sequence toolkit for Neural Machine Translation (NMT). Sockeye is a production-ready framework for training and applying models as well as an experimental platform for researchers. Written in Python and built on MXNet, the toolkit offers scalable training and inference for the three most prominent encoder-decoder architectures: attentional recurrent neural networks, self-attentional transformers, and fully convolutional networks. Sockeye also supports a wide range of optimizers, normalization and regularization techniques, and inference improvements from current NMT literature. Users can easily run standard training recipes, explore different model settings, and incorporate new ideas. In this paper, we highlight Sockeye’s features and benchmark it against other NMT toolkits on two language arcs from the 2017 Conference on Machine Translation (WMT): English-German and Latvian-English. We report competitive BLEU scores across all three architectures, including an overall best score for Sockeye’s transformer implementation. To facilitate further comparison, we release all system outputs and training scripts used in our experiments. The Sockeye toolkit is free software released under the Apache 2.0 license. |
| SOCRATES | A distributed semantic graph processing system that provides locality control, indexing, graph query, and parallel processing capabilities is presented. |
| Socratic Learning | Modern machine learning techniques, such as deep learning, often use discriminative models that require large amounts of labeled data. An alternative approach is to use a generative model, which leverages heuristics from domain experts to train on unlabeled data. Domain experts often prefer to use generative models because they ‘tell a story’ about their data. Unfortunately, generative models are typically less accurate than discriminative models. Several recent approaches combine both types of model to exploit their strengths. In this setting, a misspecified generative model can hurt the performance of subsequent discriminative training. To address this issue, we propose a framework called Socratic learning that automatically uses information from the discriminative model to correct generative model misspecification. Furthermore, this process provides users with interpretable feedback about how to improve their generative model. We evaluate Socratic learning on real-world relation extraction tasks and observe an immediate improvement in classification accuracy that could otherwise require several weeks of effort by domain experts. |
| SOD | SOD is an embedded, modern cross-platform computer vision and machine learning software library that expose a set of APIs for deep-learning, advanced media analysis & processing including real-time, multi-class object detection and model training on embedded systems with limited computational resource and IoT devices. SOD was built to provide a common infrastructure for computer vision applications and to accelerate the use of machine perception in open source as well commercial products. Designed for computational efficiency and with a strong focus on real-time applications. SOD includes a comprehensive set of both classic and state-of-the-art deep-neural networks with their pre-trained models. |
| Soft Computing (SC) |
Soft computing is a term applied to a field within computer science which is characterized by the use of inexact solutions to computationally hard tasks such as the solution of NP-complete problems, for which there is no known algorithm that can compute an exact solution in polynomial time. Soft computing differs from conventional (hard) computing in that, unlike hard computing, it is tolerant of imprecision, uncertainty, partial truth, and approximation. In effect, the role model for soft computing is the human mind. |
| Soft Concept Analysis | In this chapter we discuss soft concept analysis, a study which identifies an enriched notion of ‘conceptual scale’ as developed in formal concept analysis with an enriched notion of ‘linguistic variable’ as discussed in fuzzy logic. The identification ‘enriched conceptual scale’ = ‘enriched linguistic variable’ was made in a previous paper (Enriched interpretation, Robert E. Kent). In this chapter we offer further arguments for the importance of this identification by discussing the philosophy, spirit, and practical application of conceptual scaling to the discovery, conceptual analysis, interpretation, and categorization of networked information resources. We argue that a linguistic variable, which has been defined at just the right generalization of valuated categories, provides a natural definition for the process of soft conceptual scaling. This enrichment using valuated categories models the relation of indiscernability, a notion of central importance in rough set theory. At a more fundamental level for soft concept analysis, it also models the derivation of formal concepts, a process of central importance in formal concept analysis. Soft concept analysis is synonymous with enriched concept analysis. From one viewpoint, the study of soft concept analysis that is initiated here extends formal concept analysis to soft computational structures. From another viewpoint, soft concept analysis provides a natural foundation for soft computation by unifying and explaining notions from soft computation in terms of suitably generalized notions from formal concept analysis, rough set theory and fuzzy set theory. |
| Soft Decoupled Encoding (SDE) |
Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages. However, there are still significant challenges in efficiently learning word representations in the face of paucity of data. In this paper, we propose Soft Decoupled Encoding (SDE), a multilingual lexicon encoding framework specifically designed to share lexical-level information intelligently without requiring heuristic preprocessing such as pre-segmenting the data. SDE represents a word by its spelling through a character encoding, and its semantic meaning through a latent embedding space shared by all languages. Experiments on a standard dataset of four low-resource languages show consistent improvements over strong multilingual NMT baselines, with gains of up to 2 BLEU on one of the tested languages, achieving the new state-of-the-art on all four language pairs. |
| Soft Filter Pruning (SFP) |
This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pre-trained model. Large capacity enables SFP to train from scratch and prune the model simultaneously. In contrast, previous filter pruning methods should be conducted on the basis of the pre-trained model to guarantee their performance. Empirically, SFP from scratch outperforms the previous filter pruning methods. Moreover, our approach has been demonstrated effective for many advanced CNN architectures. Notably, on ILSCRC-2012, SFP reduces more than 42% FLOPs on ResNet-101 with even 0.2% top-5 accuracy improvement, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://…/soft-filter-pruning |
| Soft K-Means (Fuzzy C-Means) |
|
| Soft Locality Preserving Map (SLPM) |
For image recognition, an extensive number of methods have been proposed to overcome the high-dimensionality problem of feature vectors being used. These methods vary from unsupervised to supervised, and from statistics to graph-theory based. In this paper, the most popular and the state-of-the-art methods for dimensionality reduction are firstly reviewed, and then a new and more efficient manifold-learning method, named Soft Locality Preserving Map (SLPM), is presented. Furthermore, feature generation and sample selection are proposed to achieve better manifold learning. SLPM is a graph-based subspace-learning method, with the use of k-neighbourhood information and the class information. The key feature of SLPM is that it aims to control the level of spread of the different classes, because the spread of the classes in the underlying manifold is closely connected to the generalizability of the learned subspace. Our proposed manifold-learning method can be applied to various pattern recognition applications, and we evaluate its performances on facial expression recognition. Experiments on databases, such as the Bahcesehir University Multilingual Affective Face Database (BAUM-2), the Extended Cohn-Kanade (CK+) Database, the Japanese Female Facial Expression (JAFFE) Database, and the Taiwanese Facial Expression Image Database (TFEID), show that SLPM can effectively reduce the dimensionality of the feature vectors and enhance the discriminative power of the extracted features for expression recognition. Furthermore, the proposed feature-generation method can improve the generalizability of the underlying manifolds for facial expression recognition. |
| Soft Multivariate Truncated Normal Distribution (soft tMVN) |
We propose a new distribution, called the soft tMVN distribution, which provides a smooth approximation to the truncated multivariate normal (tMVN) distribution with linear constraints. An efficient blocked Gibbs sampler is developed to sample from the soft tMVN distribution in high dimensions. We provide theoretical support to the approximation capability of the soft tMVN and provide further empirical evidence thereof. The soft tMVN distribution can be used to approximate simulations from a multivariate truncated normal distribution with linear constraints, or itself as a prior in shape-constrained problems. |
| Soft Parameters Pruning (SPP) |
Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint distribution of parameters shared with all tasks. This idea can be questionable because this joint distribution may not present when the number of tasks increase. On the other hand, It also leads to ‘long-term’ memory issue when the network capacity is limited since adding tasks will ‘eat’ the network capacity. In this paper, we proposed a Soft Parameters Pruning (SPP) strategy to reach the trade-off between short-term and long-term profit of a learning model by freeing those parameters less contributing to remember former task domain knowledge to learn future tasks, and preserving memories about previous tasks via those parameters effectively encoding knowledge about tasks at the same time. The SPP also measures the importance of parameters by information entropy in a label free manner. The experiments on several tasks shows SPP model achieved the best performance compared with others state-of-the-art methods. Experiment results also indicate that our method is less sensitive to hyper-parameter and better generalization. Our research suggests that a softer strategy, i.e. approximate optimize or sub-optimal solution, will benefit alleviating the dilemma of memory. The source codes are available at https://…/Learning_by_memory. |
| Soft Probabilistic Constraint Satisfaction | This paper addresses a fundamental question of multi-agent knowledge distribution: what information should be sent to whom and when, with the limited resources available to each agent? Communication requirements for multi-agent systems can be rather high when an accurate picture of the environment and the state of other agents must be maintained. To reduce the impact of multi-agent coordination on networked systems, e.g., power and bandwidth, this paper introduces two concepts for partially observable Markov decision processes (POMDPs): 1) action-based constraints which yield constrained-action partially observable Markov decision processes (CA-POMDPs); and 2) soft probabilistic constraint satisfaction for the resulting infinite-horizon controllers. To enable constraint analysis over an infinite horizon, an unconstrained policy is first represented as a Finite State Controller (FSC) and optimized with policy iteration. The FSC representation then allows for a combination of Markov chain Monte Carlo and discrete optimization to improve the probabilistic constraint satisfaction of the controller while minimizing the impact to the value function. Within the CA-POMDP framework we then propose Intelligent Knowledge Distribution (IKD) which yields per-agent policies for distributing knowledge between agents subject to interaction constraints. Finally, the CA-POMDP and IKD concepts are validated using an asset tracking problem where multiple unmanned aerial vehicles (UAVs) with heterogeneous sensors collaborate to localize a ground asset to assist in avoiding unseen obstacles in a disaster area. The IKD model was able to maintain asset tracking through multi-agent communications while only violating soft power and bandwidth constraints 3% of the time, while greedy and naive approaches violated constraints more than 60% of the time. |
| Soft Realization | Researchers traditionally solve the computational problems through rigorous and deterministic algorithms called as Hard Computing. These precise algorithms have widely been realized using digital technology as an inherently reliable and accurate implementation platform, either in hardware or software forms. This rigid form of implementation which we refer as Hard Realization relies on strict algorithmic accuracy constraints dictated to digital design engineers. Hard realization admits paying as much as necessary implementation costs to preserve computation precision and determinism throughout all the design and implementation steps. Despite its prior accomplishments, this conventional paradigm has encountered serious challenges with today’s emerging applications and implementation technologies. Unlike traditional hard computing, the emerging soft and bio-inspired algorithms do not rely on fully precise and deterministic computation. Moreover, the incoming nanotechnologies face increasing reliability issues that prevent them from being efficiently exploited in hard realization of applications. This article examines Soft Realization, a novel bio-inspired approach to design and implementation of an important category of applications noticing the internal brain structure. The proposed paradigm mitigates major weaknesses of hard realization by (1) alleviating incompatibilities with today’s soft and bio-inspired algorithms such as artificial neural networks, fuzzy systems, and human sense signal processing applications, and (2) resolving the destructive inconsistency with unreliable nanotechnologies. Our experimental results on a set of well-known soft applications implemented using the proposed soft realization paradigm in both reliable and unreliable technologies indicate that significant energy, delay, and area savings can be obtained compared to the conventional implementation. |
| Soft Topographic Vector Quantization (STVQ) |
We have developed an algorithm (STVQ) for the optimization of neighbourhood preserving maps by applying deterministic annealing to an energy function for topographic vector quantization. The combinatorial optimization problem is solved by introducing temperature dependent fuzzy assignments of data points to cluster centers and applying an EM-type algorithm at each temperature while annealing. The annealing process exhibits phase transitions in the cluster representation for which we calcul ate critical modes and temperatures expressed in terms of the neighbourhood function and the covariance matrix of the data. In particular, phase transitions corresponding to the automatic selection of feature dimensions are explored analytically and numer ically for finite temperatures. Results are related to those obtained earlier for Kohonen’s SOM-algorithm which can be derived as an approximation to STVQ. The deterministic annealing approach makes it possible to use the neighbourhood function solely to encode desired neighbourhood relations. The working of the annealing process is visualized by showing the effects of ‘heating’ on the topological structure of a two-dimensional map of the plane. |
| Soft-Autoencoder (Soft-AE) |
Deep learning is a main focus of artificial intelligence and has greatly impacted other fields. However, deep learning is often criticized for its lack of interpretation. As a successful unsupervised model in deep learning, various autoencoders, especially convolutional autoencoders, are very popular and important. Since these autoencoders need improvements and insights, in this paper we shed light on the nonlinearity of a deep convolutional autoencoder in perspective of perfect signal recovery. In particular, we propose a new type of convolutional autoencoders, termed as Soft-Autoencoder (Soft-AE), in which the activations of encoding layers are implemented with adaptable soft-thresholding units while decoding layers are realized with linear units. Consequently, Soft-AE can be naturally interpreted as a learned cascaded wavelet shrinkage system. Our denoising numerical experiments on CIFAR-10, BSD-300 and Mayo Clinical Challenge Dataset demonstrate that Soft-AE gives a competitive performance relative to its counterparts. |
| Softer-Non-Maximum Suppression (Softer-NMS) |
Non-maximum suppression (NMS) is essential for state-of-the-art object detectors to localize object from a set of candidate locations. However, accurate candidate location sometimes is not associated with a high classification score, which leads to object localization failure during NMS. In this paper, we introduce a novel bounding box regression loss for learning bounding box transformation and localization variance together. The resulting localization variance exhibits a strong connection to localization accuracy, which is then utilized in our new non-maximum suppression method to improve localization accuracy for object detection. On MS-COCO, we boost the AP of VGG-16 faster R-CNN from 23.6% to 29.1% with a single model and nearly no additional computational overhead. More importantly, our method is able to improve the AP of ResNet-50 FPN fast R-CNN from 36.8% to 37.8%, which achieves state-of-the-art bounding box refinement result. |
| Soft-Guided Adaptively-Dropped Neural Network (SGAD) |
Deep neural networks (DNNs) have been proven to have many redundancies. Hence, many efforts have been made to compress DNNs. However, the existing model compression methods treat all the input samples equally while ignoring the fact that the difficulties of various input samples being correctly classified are different. To address this problem, DNNs with adaptive dropping mechanism are well explored in this work. To inform the DNNs how difficult the input samples can be classified, a guideline that contains the information of input samples is introduced to improve the performance. Based on the developed guideline and adaptive dropping mechanism, an innovative soft-guided adaptively-dropped (SGAD) neural network is proposed in this paper. Compared with the 32 layers residual neural networks, the presented SGAD can reduce the FLOPs by 77% with less than 1% drop in accuracy on CIFAR-10. |
| Softmax Feature Fusion Module (SFFM) |
Single image super-resolution(SISR) has witnessed great progress as convolutional neural network(CNN) gets deeper and wider. However, enormous parameters hinder its application to real world problems. In this letter, We propose a lightweight feature fusion network (LFFN) that can fully explore multi-scale contextual information and greatly reduce network parameters while maximizing SISR results. LFFN is built on spindle blocks and a softmax feature fusion module (SFFM). Specifically, a spindle block is composed of a dimension extension unit, a feature exploration unit and a feature refinement unit. The dimension extension layer expands low dimension to high dimension and implicitly learns the feature maps which is suitable for the next unit. The feature exploration unit performs linear and nonlinear feature exploration aimed at different feature maps. The feature refinement layer is used to fuse and refine features. SFFM fuses the features from different modules in a self-adaptive learning manner with softmax function, making full use of hierarchical information with a small amount of parameter cost. Both qualitative and quantitative experiments on benchmark datasets show that LFFN achieves favorable performance against state-of-the-art methods with similar parameters. |
| Soft-Robust Actor-Critic algorithm (SR-AC) |
Robust Reinforcement Learning aims to derive an optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly conservative. Our \textit{soft-robust} framework is an attempt to overcome this issue. In this paper, we present a novel Soft-Robust Actor-Critic algorithm (SR-AC). It learns an optimal policy with respect to a distribution over an uncertainty set and stays robust to model uncertainty but avoids the conservativeness of robust strategies. We show convergence of the SR-AC and test the efficiency of our approach on different domains by comparing it against regular learning methods and their robust formulations. |
| SoftTarget Regularization | Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropCon- nect, and weight decay all attempt to solve the problem of over-fitting by reducing the capacity of their respective models (Srivastava et al., 2014), (Wan et al., 2013), (Krogh & Hertz, 1992). In this paper we introduce a new form of regularization that guides the learning problem in a way that reduces over-fitting without sacrificing the capacity of the model. The mistakes that models make in early stages of training carry information about the learning problem. By adjusting the labels of the current epoch of training through a weighted average of the real labels, and an exponential average of the past soft-targets we achieved a regularization scheme as powerful as Dropout without necessarily reducing the capacity of the model, and simplified the complexity of the learning problem. SoftTarget regularization proved to be an effective tool in various neural network architectures. |
| Sogou Machine Reading Comprehension (SMRC) |
Machine reading comprehension have been intensively studied in recent years, and neural network-based models have shown dominant performances. In this paper, we present a Sogou Machine Reading Comprehension (SMRC) toolkit that can be used to provide the fast and efficient development of modern machine comprehension models, including both published models and original prototypes. To achieve this goal, the toolkit provides dataset readers, a flexible preprocessing pipeline, necessary neural network components, and built-in models, which make the whole process of data preparation, model construction, and training easier. |
| SolarMapper | The effective integration of distributed solar photovoltaic (PV) arrays into existing power grids will require access to high quality data; the location, power capacity, and energy generation of individual solar PV installations. Unfortunately, existing methods for obtaining this data are limited in their spatial resolution and completeness. We propose a general framework for accurately and cheaply mapping individual PV arrays, and their capacities, over large geographic areas. At the core of this approach is a deep learning algorithm called SolarMapper – which we make publicly available – that can automatically map PV arrays in high resolution overhead imagery. We estimate the performance of SolarMapper on a large dataset of overhead imagery across three US cities in California. We also describe a procedure for deploying SolarMapper to new geographic regions, so that it can be utilized by others. We demonstrate the effectiveness of the proposed deployment procedure by using it to map solar arrays across the entire US state of Connecticut (CT). Using these results, we demonstrate that we achieve highly accurate estimates of total installed PV capacity within each of CT’s 168 municipal regions. |
| Solid | Solid (derived from ‘social linked data’) is a proposed set of conventions and tools for building decentralized Web applications based on Linked Data principles. Solid is modular and extensible. It relies as much as possible on existing W3C standards and protocols. |
| Solver-Quality | Algorithmic assurances from advanced autonomous systems assist human users in understanding, trusting, and using such systems appropriately. Designing these systems with the capacity of assessing their own capabilities is one approach to creating an algorithmic assurance. The idea of `machine self-confidence’ is introduced for autonomous systems. Using a factorization based framework for self-confidence assessment, one component of self-confidence, called `solver-quality’, is discussed in the context of Markov decision processes for autonomous systems. Markov decision processes underlie much of the theory of reinforcement learning, and are commonly used for planning and decision making under uncertainty in robotics and autonomous systems. A `solver quality’ metric is formally defined in the context of decision making algorithms based on Markov decision processes. A method for assessing solver quality is then derived, drawing inspiration from empirical hardness models. Finally, numerical experiments for an unmanned autonomous vehicle navigation problem under different solver, parameter, and environment conditions indicate that the self-confidence metric exhibits the desired properties. Discussion of results, and avenues for future investigation are included. |
| Sonification | Sonification is the use of non-speech audio to convey information or perceptualize data. Auditory perception has advantages in temporal, spatial, amplitude, and frequency resolution that open possibilities as an alternative or complement to visualization techniques. For example, the rate of clicking of a Geiger counter conveys the level of radiation in the immediate vicinity of the device. Though many experiments with data sonification have been explored in forums such as the International Community for Auditory Display (ICAD), sonification faces many challenges to widespread use for presenting and analyzing data. For example, studies show it is difficult, but essential, to provide adequate context for interpreting sonifications of data. Many sonification attempts are coded from scratch due to the lack of a flexible tool for sonification research and data exploration Turning Data into Sound |
| Sonnet | It’s now nearly a year since DeepMind made the decision to switch the entire research organisation to using TensorFlow (TF). It’s proven to be a good choice – many of our models learn significantly faster, and the built-in features for distributed training have hugely simplified our code. Along the way, we found that the flexibility and adaptiveness of TF lends itself to building higher level frameworks for specific purposes, and we’ve written one for quickly building neural network modules with TF. We are actively developing this codebase, but what we have so far fits our research needs well, and we’re excited to announce that today we are open sourcing it. We call this framework Sonnet. |
| Sorites Paradox | The sorites paradox (sometimes known as the paradox of the heap) is a paradox that arises from vague predicates. A typical formulation involves a heap of sand, from which grains are individually removed. Under the assumption that removing a single grain does not turn a heap into a non-heap, the paradox is to consider what happens when the process is repeated enough times: is a single remaining grain still a heap? If not, when did it change from a heap to a non-heap? |
| Sorting Deep net (SoDeep) |
Several tasks in machine learning are evaluated using non-differentiable metrics such as mean average precision or Spearman correlation. However, their non-differentiability prevents from using them as objective functions in a learning framework. Surrogate and relaxation methods exist but tend to be specific to a given metric. In the present work, we introduce a new method to learn approximations of such non-differentiable objective functions. Our approach is based on a deep architecture that approximates the sorting of arbitrary sets of scores. It is trained virtually for free using synthetic data. This sorting deep (SoDeep) net can then be combined in a plug-and-play manner with existing deep architectures. We demonstrate the interest of our approach in three different tasks that require ranking: Cross-modal text-image retrieval, multi-label image classification and visual memorability ranking. Our approach yields very competitive results on these three tasks, which validates the merit and the flexibility of SoDeep as a proxy for sorting operation in ranking-based losses. |
| Soundex | Soundex is a phonetic algorithm for indexing names by sound, as pronounced in English. The goal is for homophones to be encoded to the same representation so that they can be matched despite minor differences in spelling. The algorithm mainly encodes consonants; a vowel will not be encoded unless it is the first letter. Soundex is the most widely known of all phonetic algorithms (in part because it is a standard feature of popular database software such as DB2, PostgreSQL, MySQL, Ingres, MS SQL Server and Oracle) and is often used (incorrectly) as a synonym for “phonetic algorithm”. Improvements to Soundex are the basis for many modern phonetic algorithms. |
| Sounding Board | We present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize. The system architecture consists of several components including spoken language processing, dialogue management, language generation, and content management, with emphasis on user-centric and content-driven design. We also share insights gained from large-scale online logs based on 160,000 conversations with real-world users. |
| Source Localization Via an Iterative Technique (SOLVIT) |
We consider the problem of localizing the source using range and range-difference measurements. Both the problems are known to be non-convex and non-smooth, which makes it challenging to solve. In the case of range-difference measurements, most of the current positioning techniques choose a reference sensor, however the source positioning accuracy has been reported to be affected by this approach. In this paper, we localize the source from range-difference measurements without choosing a reference sensor. We develop an iterative algorithm to solve the range-difference problem using Majorization Minimization (MM) approach-in which we employ a novel upper bound and minimize it to get a closed form solution at every iteration. The proposed algorithm is referred to as SOLVIT: Source Localization Via an Iterative technique. We also solve the source localization problem based on range measurements and rederive the Standard Fixed Point (SFP) algorithm developed in [1] using the MM approach. By doing so, we show a less intricate way to prove the convergence of the SFP algorithm. Next, we show a computationally efficient way to implement SOLVIT. Various simulations and experiments were conducted to compare SOLVIT with the existing methods. Experiments were conducted in an anechoic chamber to localize an acoustic source. Simulations and experiments confirm that SOLVIT performs better than existing methods in terms of source positioning accuracy. Also, it was found that when compared to the existing methods, SOLVIT does not depend on the positioning of source and sensors to localize a source. |
| Sourcegraph | Sourcegraph is a fast, open-source, fully-featured code search and navigation engine. |
| Source-Guided Discrepancy (S-disc) |
Unsupervised domain adaptation is the problem setting where data generating distributions in the source and target domains are different, and labels in the target domain are unavailable. One important question in unsupervised domain adaptation is how to measure the difference between the source and target domains. A previously proposed discrepancy that does not use the source domain labels requires high computational cost to estimate and may lead to a loose generalization error bound in the target domain.To mitigate these problems, we propose a novel discrepancy called source-guided discrepancy ($S$-disc), which exploits labels in the source domain. As a consequence, $S$-disc can be computed efficiently with a finite sample convergence guarantee. In addition, we show that $S$-disc can provide a tighter generalization error bound than the one based on an existing discrepancy. Finally, we report experimental results that demonstrate the advantages of $S$-disc over the existing discrepancies. |
| Spacetime | We look at one important category of distributed applications characterized by the existence of multiple collaborating, and competing, components sharing mutable, long-lived, replicated objects. The problem addressed by our work is that of object state synchronization among the components. As an organizing principle for replicated objects, we formally specify the Global Object Tracker (GoT) model, an object-oriented programming model based on causal consistency with application-level conflict resolution strategies, whose elements and interfaces mirror those found in decentralized version control systems: a version graph, working data, diffs, commit, checkout, fetch, push, and merge. We have implemented GoT in a framework called Spacetime, written in Python. In its purest form, GoT is impractical for real systems, because of the unbounded growth of the version graph and because passing diff’ed histories over the network makes remote communication too slow. We present our solution to these problems that adds some constraints to GoT applications, but that makes the model feasible in practice. We present a performance analysis of Spacetime for representative workloads, which shows that the additional constraints added to GoT make it not just feasible, but viable for real applications. |
| spaCy | spaCy, aIndustrial-strength NLP, is a library for advanced natural language processing in Python and Cython. spaCy is built on the very latest research, but it isn’t researchware. It was designed from day 1 to be used in real products. You can buy a commercial license, or you can use it under the AGPL. Features: · Labelled dependency parsing (91.8% accuracy on OntoNotes 5) · Named entity recognition (82.6% accuracy on OntoNotes 5) · Part-of-speech tagging (97.1% accuracy on OntoNotes 5) · Easy to use word vectors · All strings mapped to integer IDs · Export to numpy data arrays · Alignment maintained to original string, ensuring easy mark up calculation · Range of easy-to-use orthographic features. · No pre-processing required. spaCy takes raw text as input, warts and newlines and all. Github |
| Spaghetti Plot | A spaghetti plot (also known as a spaghetti chart, spaghetti diagram, or spaghetti model) is a method of viewing data to visualize possible flows through systems. Flows depicted in this manner appear like noodles, hence the coining of this term. This method of statistics was first used to track routing through factories. Visualizing flow in this manner can reduce inefficiency within the flow of a system. In regards to animal populations and weather buoys drifting through the ocean, they are drawn to study distribution and migration patterns. Within meteorology, these diagrams can help determine confidence in a specific weather forecast, as well as positions and intensities of high and low pressure systems. They are composed of deterministic forecasts from atmospheric models or their various ensemble members. Within medicine, they can illustrate the effects of drugs on patients during drug trials. |
| spamGAN | Online reviews have become a vital source of information in purchasing a service (product). Opinion spammers manipulate reviews, affecting the overall perception of the service. A key challenge in detecting opinion spam is obtaining ground truth. Though there exists a large set of reviews online, only a few of them have been labeled spam or non-spam. In this paper, we propose spamGAN, a generative adversarial network which relies on limited set of labeled data as well as unlabeled data for opinion spam detection. spamGAN improves the state-of-the-art GAN based techniques for text classification. Experiments on TripAdvisor dataset show that spamGAN outperforms existing spam detection techniques when limited labeled data is used. Apart from detecting spam reviews, spamGAN can also generate reviews with reasonable perplexity. |
| SPARCML | One of the main drivers behind the rapid recent advances in machine learning has been the availability of efficient system support. This comes both through hardware acceleration, but also in the form of efficient software frameworks and programming models. Despite significant progress, scaling compute-intensive machine learning workloads to a large number of compute nodes is still a challenging task, with significant latency and bandwidth demands. In this paper, we address this challenge, by proposing SPARCML, a general, scalable communication layer for machine learning applications. SPARCML is built on the observation that many distributed machine learning algorithms either have naturally sparse communication patters, or have updates which can be sparsified in a structured way for improved performance, without any convergence or accuracy loss. To exploit this insight, we design and implement a set of communication efficient protocols for sparse input data, in conjunction with efficient machine learning algorithms which can leverage these primitives. Our communication protocols generalize standard collective operations, by allowing processes to contribute sparse input data vectors, of heterogeneous sizes. We call these operations sparse-input collectives, and present efficient practical algorithms with strong theoretical bounds on their running time and communication cost. Our generic communication layer is enriched with additional features, such support for non-blocking (asynchronous) operations, and support for low-precision data representations. We validate our algorithmic results experimentally on a range of large-scale machine learning applications and target architectures, showing that we can leverage sparsity for order- of-magnitude runtime savings, compared to state-of-the art methods and frameworks. |
| Spark Python API (PySpark) |
The Spark Python API (PySpark) exposes the Spark programming model to Python. To learn the basics of Spark, we recommend reading through the Scala programming guide first; it should be easy to follow even if you don’t know Scala. This guide will show how to use the Spark features described there in Python. PySpark & Scikit-learn = Sparkit-learn |
| Spark Serving | ➚ “Microsoft Machine Learning for Apache Spark” |
| Sparkle | Spark is an in-memory analytics platform that targets commodity server environments today. It relies on the Hadoop Distributed File System (HDFS) to persist intermediate checkpoint states and final processing results. In Spark, immutable data are used for storing data updates in each iteration, making it inefficient for long running, iterative workloads. A non-deterministic garbage collector further worsens this problem. Sparkle is a library that optimizes memory usage in Spark. It exploits large shared memory to achieve better data shuffling and intermediate storage. Sparkle replaces the current TCP/IP-based shuffle with a shared memory approach and proposes an off-heap memory store for efficient updates. We performed a series of experiments on scale-out clusters and scale-up machines. The optimized shuffle engine leveraging shared memory provides 1.3x to 6x faster performance relative to Vanilla Spark. The off-heap memory store along with the shared-memory shuffle engine provides more than 20x performance increase on a probabilistic graph processing workload that uses a large-scale real-world hyperlink graph. While Sparkle benefits at most from running on large memory machines, it also achieves 1.6x to 5x performance improvements over scale out cluster with equivalent hardware setting. |
| SparkNet | Training deep networks is a time-consuming process, with networks for object recognition often requiring multiple days to train. For this reason, leveraging the resources of a cluster to speed up training is an important area of work. However, widely-popular batch-processing computational frameworks like MapReduce and Spark were not designed to support the asynchronous and communication-intensive workloads of existing distributed deep learning systems. We introduce SparkNet, a framework for training deep networks in Spark. Our implementation includes a convenient interface for reading data from Spark RDDs, a Scala interface to the Caffe deep learning framework, and a lightweight multi-dimensional tensor library. Using a simple parallelization scheme for stochastic gradient descent, SparkNet scales well with the cluster size and tolerates very high-latency communication. Furthermore, it is easy to deploy and use with no parameter tuning, and it is compatible with existing Caffe models. We quantify the dependence of the speedup obtained by SparkNet on the number of machines, the communication frequency, and the cluster’s communication overhead, and we benchmark our system’s performance on the ImageNet dataset. |
| SPARQL Protocol and RDF Query Language (SPARQL) |
SPARQL (pronounced “sparkle”, a recursive acronym for SPARQL Protocol and RDF Query Language) is an RDF query language, that is, a semantic query language for databases, able to retrieve and manipulate data stored in Resource Description Framework format. It was made a standard by the RDF Data Access Working Group (DAWG) of the World Wide Web Consortium, and is recognized as one of the key technologies of the semantic web. On 15 January 2008, SPARQL 1.0 became an official W3C Recommendation, and SPARQL 1.1 in March, 2013. SPARQL allows for a query to consist of triple patterns, conjunctions, disjunctions, and optional patterns. Implementations for multiple programming languages exist. “SPARQL will make a huge difference” making the web machine-readable according to Sir Tim Berners-Lee in a May 2006 interview. There exist tools that allow one to connect and semi-automatically construct a SPARQL query for a SPARQL endpoint, for example ViziQuer. In addition, there exist tools that translate SPARQL queries to other query languages, for example to SQL and to XQuery. |
| Sparse Coding | The sparse code is when each item is encoded by the strong activation of a relatively small set of neurons. For each item to be encoded, this is a different subset of all available neurons. As a consequence, sparseness may be focused on temporal sparseness (‘a relatively small number of time periods are active’) or on the sparseness in an activated population of neurons. In this latter case, this may be defined in one time period as the number of activated neurons relative to the total number of neurons in the population. This seems to be a hallmark of neural computations since compared to traditional computers, information is massively distributed across neurons. A major result in neural coding from Olshausen et al. is that sparse coding of natural images produces wavelet-like oriented filters that resemble the receptive fields of simple cells in the visual cortex. The capacity of sparse codes may be increased by simultaneous use of temporal coding, as found in the locust olfactory system. Given a potentially large set of input patterns, sparse coding algorithms (e.g. Sparse Autoencoder) attempt to automatically find a small number of representative patterns which, when combined in the right proportions, reproduce the original input patterns. The sparse coding for the input then consists of those representative patterns. For example, the very large set of English sentences can be encoded by a small number of symbols (i.e. letters, numbers, punctuation, and spaces) combined in a particular order for a particular sentence, and so a sparse coding for English would be those symbols. ➚ “Dictionary Learning” More Algorithms for Provable Dictionary Learning |
| Sparse Constraint Preserving Matching (SPM) |
Many problems of interest in computer vision can be formulated as a problem of finding consistent correspondences between two feature sets. Feature correspondence (matching) problem with one-to-one mapping constraint is usually formulated as an Integral Quadratic Programming (IQP) problem with permutation (or orthogonal) constraint. Since it is NP-hard, relaxation models are required. One main challenge for optimizing IQP matching problem is how to incorporate the discrete one-to-one mapping (permutation) constraint in its quadratic objective optimization. In this paper, we present a new relaxation model, called Sparse Constraint Preserving Matching (SPM), for IQP matching problem. SPM is motivated by our observation that the discrete permutation constraint can be well encoded via a sparse constraint. Comparing with traditional relaxation models, SPM can incorporate the discrete one-to-one mapping constraint straightly via a sparse constraint and thus provides a tighter relaxation for original IQP matching problem. A simple yet effective update algorithm has been derived to solve the proposed SPM model. Experimental results on several feature matching tasks demonstrate the effectiveness and efficiency of SPM method. |
| Sparse Deep Predictive Coding (SDPC) |
Convolutional Neural Networks (CNNs) are the state-of-the-art algorithms used in computer vision. However, these models often suffer from the lack of interpretability of their information transformation process. To address this problem, we introduce a novel model called Sparse Deep Predictive Coding (SDPC). In a biologically realistic manner, SDPC mimics how the brain is efficiently representing visual information. This model complements the hierarchical convolutional layers found in CNNs with the feed-forward and feed-back update scheme described in the Predictive Coding (PC) theory and found in the architecture of the mammalian visual system. We experimentally demonstrate on two databases that the SDPC model extracts qualitatively meaningful features. These features, besides being similar to some of the biological Receptive Fields of the visual cortex, also represent hierarchically independent components of the image that are crucial to describe it in a generic manner. For the first time, the SDPC model demonstrates a meaningful representation of features within the hierarchical generative model and of the decision-making process leading to a specific prediction. A quantitative analysis reveals that the features extracted by the SDPC model encode the input image into a representation that is both easily classifiable and robust to noise. |
| Sparse Distributed Representations (SDR) |
Sparse Distributed Representations are binary representations of data comprised of many bits with a small percentage of the bits active (1’s). The bits in these representations have semantic meaning and that meaning is distributed across the bits. https://…-distributed-representations-sparse-codes |
| Sparse Gaussian Processes With Q-Function (SGP-Q) |
Online anomaly detection of time-series data is an important and challenging task in machine learning. Gaussian processes (GPs) are powerful and flexible models for modeling time-series data. However, the high time complexity of GPs limits their applications in online anomaly detection. Attributed to some internal or external changes, concept drift usually occurs in time-series data, where the characteristics of data and meanings of abnormal behaviors alter over time. Online anomaly detection methods should have the ability to adapt to concept drift. Motivated by the above facts, this paper proposes the method of sparse Gaussian processes with Q-function (SGP-Q). The SGP-Q employs sparse Gaussian processes (SGPs) whose time complexity is lower than that of GPs, thus significantly speeding up online anomaly detection. By using Q-function properly, the SGP-Q can adapt to concept drift well. Moreover, the SGP-Q makes use of few abnormal data in the training data by its strategy of updating training data, resulting in more accurate sparse Gaussian process regression models and better anomaly detection results. We evaluate the SGP-Q on various artificial and real-world datasets. Experimental results validate the effectiveness of the SGP-Q. |
| Sparse Generalized Linear Models | glmgraph |
| SParse Interpretable Neural Embeddings (SPINE) |
Prediction without justification has limited utility. Much of the success of neural models can be attributed to their ability to learn rich, dense and expressive representations. While these representations capture the underlying complexity and latent trends in the data, they are far from being interpretable. We propose a novel variant of denoising k-sparse autoencoders that generates highly efficient and interpretable distributed word representations (word embeddings), beginning with existing word representations from state-of-the-art methods like GloVe and word2vec. Through large scale human evaluation, we report that our resulting word embedddings are much more interpretable than the original GloVe and word2vec embeddings. Moreover, our embeddings outperform existing popular word embeddings on a diverse suite of benchmark downstream tasks. |
| Sparse Linear Isotonic Model | In machine learning and data mining, linear models have been widely used to model the response as parametric linear functions of the predictors. To relax such stringent assumptions made by parametric linear models, additive models consider the response to be a summation of unknown transformations applied on the predictors; in particular, additive isotonic models (AIMs) assume the unknown transformations to be monotone. In this paper, we introduce sparse linear isotonic models (SLIMs) for highdimensional problems by hybridizing ideas in parametric sparse linear models and AIMs, which enjoy a few appealing advantages over both. In the high-dimensional setting, a two-step algorithm is proposed for estimating the sparse parameters as well as the monotone functions over predictors. Under mild statistical assumptions, we show that the algorithm can accurately estimate the parameters. Promising preliminary experiments are presented to support the theoretical results. |
| Sparse Linear Method (SLIM) |
This paper focuses on developing effective and efficient algorithms for top-N recommender systems. A novel Sparse LInear Method (SLIM) is proposed, which generates topN recommendations by aggregating from user purchase/rating profiles. A sparse aggregation coefficient matrix W is learned from SLIM by solving an l1-norm and l2-norm regularized optimization problem. W is demonstrated to produce highquality recommendations and its sparsity allows SLIM to generate recommendations very fast. A comprehensive set of experiments is conducted by comparing the SLIM method and other state-ofthe-art top-N recommendation methods. The experiments show that SLIM achieves significant improvements both in run time performance and recommendation quality over the best existing methods. GitXiv slimrec |
| Sparse Matrix / Sparsity | In numerical analysis, a sparse matrix is a matrix in which most of the elements are zero. By contrast, if most of the elements are nonzero, then the matrix is considered dense. The fraction of zero elements (non-zero elements) in a matrix is called the sparsity (density). Sparsity is in the general sense: variable selection, total variation regularization, polynomial trend filtering, and others. http://…/demo_glm.html |
| Sparse Matrix-Based SPARQL (SM-based SPARQL,gSMat) |
Resource Description Framework (RDF) has been widely used to represent information on the web, while SPARQL is a standard query language to manipulate RDF data. Given a SPARQL query, there often exist many joins which are the bottlenecks of efficiency of query processing. Besides, the real RDF datasets often reveal strong data sparsity, which indicates that a resource often only relates to a few resources even the number of total resources is large. In this paper, we propose a sparse matrix-based (SM-based) SPARQL query processing approach over RDF datasets which con- siders both join optimization and data sparsity. Firstly, we present a SM-based storage for RDF datasets to lift the storage efficiency, where valid edges are stored only, and then introduce a predicate- based hash index on the storage. Secondly, we develop a scalable SM-based join algorithm for SPARQL query processing. Finally, we analyze the overall cost by accumulating all intermediate results and design a query plan generated algorithm. Besides, we extend our SM-based join algorithm on GPU for parallelizing SPARQL query processing. We have evaluated our approach compared with the state-of-the-art RDF engines over benchmark RDF datasets and the experimental results show that our proposal can significantly improve SPARQL query processing with high scalability. |
| Sparse Multiprototype Linear Learner (SMaLL) |
We present a new machine learning technique for training small resource-constrained predictors. Our algorithm, the Sparse Multiprototype Linear Learner (SMaLL), is inspired by the classic machine learning problem of learning $k$-DNF Boolean formulae. We present a formal derivation of our algorithm and demonstrate the benefits of our approach with a detailed empirical study. |
| Sparse Neural Network Decoder (SNND) |
In this paper, we present a sparse neural network decoder (SNND) of polar codes based on belief propagation (BP) and deep learning. At first, the conventional factor graph of polar BP decoding is converted to the bipartite Tanner graph similar to low-density parity-check (LDPC) codes. Then the Tanner graph is unfolded and translated into the graphical representation of deep neural network (DNN). The complex sum-product algorithm (SPA) is modified to min-sum (MS) approximation with low complexity. We dramatically reduce the number of weight by using single weight to parameterize the networks. Optimized by the training techniques of deep learning, proposed SNND achieves comparative decoding performance of SPA and obtains about $0.5$ dB gain over MS decoding on ($128,64$) and ($256,128$) codes. Moreover, $60 \%$ complexity reduction is achieved and the decoding latency is significantly lower than the conventional polar BP. |
| Sparse Principal Component Analysis (SPCA) |
Sparse principal component analysis (sparse PCA) is a specialised technique used in statistical analysis and, in particular, in the analysis of multivariate data sets. It extends the classic method of principal component analysis (PCA) for the reduction of dimensionality of data by adding sparsity constraint on the input variables. Ordinary principal component analysis (PCA) uses a vector space transform to reduce multidimensional data sets to lower dimensions. It finds linear combinations of input variables, and transforms them into new variables (called principal components) that correspond to directions of maximal variance in the data. The number of new variables created by these linear combinations is usually much lower than the number of input variables in the original dataset, while still explaining most of the variance present in the data. A particular disadvantage of ordinary PCA is that the principal components are usually linear combinations of all input variables. Sparse PCA overcomes this disadvantage by finding linear combinations that contain just a few input variables. |
| Sparse Shrink | Nowadays, it is still difficult to adapt Convolutional Neural Network (CNN) based models for deployment on embedded devices. The heavy computation and large memory footprint of CNN models become the main burden in real application. In this paper, we propose a ‘Sparse Shrink’ algorithm to prune an existing CNN model. By analyzing the importance of each channel via sparse reconstruction, the algorithm is able to prune redundant feature maps accordingly. The resulting pruned model thus directly saves computational resource. We have evaluated our algorithm on CIFAR-100. As shown in our experiments, we can reduce 56.77% parameters and 73.84% multiplication in total with only minor decrease in accuracy. These results have demonstrated the effectiveness of our ‘Sparse Shrink’ algorithm. |
| Sparse Space-Time Model | Inspired by Kalikow-type decompositions, we introduce a new stochastic model of infinite neuronal networks, for which we establish oracle inequalities for Lasso methods and restricted eigenvalue properties for the associated Gram matrix with high probability. These results hold even if the network is only partially observed. The main argument rely on the fact that concentration inequalities can easily be derived whenever the transition probabilities of the underlying process admit a sparse space-time representation. |
| Sparse Spatial Generalized Linear Mixed Model (SGLMM) |
(reparameterizations of traditional models) ngspatial |
| Sparse Tensor Additive Regression (STAR) |
Tensors are becoming prevalent in modern applications such as medical imaging and digital marketing. In this paper, we propose a sparse tensor additive regression (STAR) that models a scalar response as a flexible nonparametric function of tensor covariates. The proposed model effectively exploits the sparse and low-rank structures in the tensor additive regression. We formulate the parameter estimation as a non-convex optimization problem, and propose an efficient penalized alternating minimization algorithm. We establish a non-asymptotic error bound for the estimator obtained from each iteration of the proposed algorithm, which reveals an interplay between the optimization error and the statistical rate of convergence. We demonstrate the efficacy of STAR through extensive comparative simulation studies, and an application to the click-through-rate prediction in online advertising. |
| Sparse Ternary Compression (STC) |
Federated Learning allows multiple parties to jointly train a deep learning model on their combined data, without any of the participants having to reveal their local data to a centralized server. This form of privacy-preserving collaborative learning however comes at the cost of a significant communication overhead during training. To address this problem, several compression methods have been proposed in the distributed training literature that can reduce the amount of required communication by up to three orders of magnitude. These existing methods however are only of limited utility in the Federated Learning setting, as they either only compress the upstream communication from the clients to the server (leaving the downstream communication uncompressed) or only perform well under idealized conditions such as iid distribution of the client data, which typically can not be found in Federated Learning. In this work, we propose Sparse Ternary Compression (STC), a new compression framework that is specifically designed to meet the requirements of the Federated Learning environment. Our experiments on four different learning tasks demonstrate that STC distinctively outperforms Federated Averaging in common Federated Learning scenarios where clients either a) hold non-iid data, b) use small batch sizes during training, or where c) the number of clients is large and the participation rate in every communication round is low. We furthermore show that even if the clients hold iid data and use medium sized batches for training, STC still behaves pareto-superior to Federated Averaging in the sense that it achieves fixed target accuracies on our benchmarks within both fewer training iterations and a smaller communication budget. |
| Sparse Transformer | Transformers are powerful sequence models, but require time and memory that grows quadratically with the sequence length. In this paper we introduce sparse factorizations of the attention matrix which reduce this to $O(n \sqrt{n})$. We also introduce a) a variation on architecture and initialization to train deeper networks, b) the recomputation of attention matrices to save memory, and c) fast attention kernels for training. We call networks with these changes Sparse Transformers, and show they can model sequences tens of thousands of timesteps long using hundreds of layers. We use the same architecture to model images, audio, and text from raw bytes, setting a new state of the art for density modeling of Enwik8, CIFAR-10, and ImageNet-64. We generate unconditional samples that demonstrate global coherence and great diversity, and show it is possible in principle to use self-attention to model sequences of length one million or more. |
| Sparse Unscented Kalman Filter (sparse UKF) |
Several variations of the Kalman filter algorithm, such as the extended Kalman filter (EKF) and the unscented Kalman filter (UKF), are widely used in science and engineering applications. In this paper, we introduce two algorithms of sparsity-based Kalman filters, namely the sparse UKF and the progressive EKF. The filters are designed specifically for problems with very high dimensions. Different from various types of ensemble Kalman filters (EnKFs) in which the error covariance is approximated using a set of dense ensemble vectors, the algorithms developed in this paper are based on sparse matrix approximations of error covariance. The new algorithms enjoy several advantages. The error covariance has full rank without being limited by a set of ensembles. In addition to the estimated states, the algorithms provide updated error covariance for the next assimilation cycle. The sparsity of error covariance significantly reduces the required memory size for the numerical computation. In addition, the granularity of the sparse error covariance can be adjusted to optimize the parallelization of the algorithms. |
| Sparse Weighted Canonical Correlation Analysis (SWCCA) |
Given two data matrices $X$ and $Y$, sparse canonical correlation analysis (SCCA) is to seek two sparse canonical vectors $u$ and $v$ to maximize the correlation between $Xu$ and $Yv$. However, classical and sparse CCA models consider the contribution of all the samples of data matrices and thus cannot identify an underlying specific subset of samples. To this end, we propose a novel sparse weighted canonical correlation analysis (SWCCA), where weights are used for regularizing different samples. We solve the $L_0$-regularized SWCCA ($L_0$-SWCCA) using an alternating iterative algorithm. We apply $L_0$-SWCCA to synthetic data and real-world data to demonstrate its effectiveness and superiority compared to related methods. Lastly, we consider also SWCCA with different penalties like LASSO (Least absolute shrinkage and selection operator) and Group LASSO, and extend it for integrating more than three data matrices. |
| Sparsely Connected Convolutional Network (SparseNet) |
Residual learning with skip connections permits training ultra-deep neural networks and obtains superb performance. Building in this direction, DenseNets proposed a dense connection structure where each layer is directly connected to all of its predecessors. The densely connected structure leads to better information flow and feature reuse. However, the overly dense skip connections also bring about the problems of potential risk of overfitting, parameter redundancy and large memory consumption. In this work, we analyze the feature aggregation patterns of ResNets and DenseNets under a uniform aggregation view framework. We show that both structures densely gather features from previous layers in the network but combine them in their respective ways: summation (ResNets) or concatenation (DenseNets). We compare the strengths and drawbacks of these two aggregation methods and analyze their potential effects on the networks’ performance. Based on our analysis, we propose a new structure named SparseNets which achieves better performance with fewer parameters than DenseNets and ResNets. |
| SparseNet | Deep neural networks have made remarkable progresses on various computer vision tasks. Recent works have shown that depth, width and shortcut connections of networks are all vital to their performances. In this paper, we introduce a method to sparsify DenseNet which can reduce connections of a L-layer DenseNet from O(L^2) to O(L), and thus we can simultaneously increase depth, width and connections of neural networks in a more parameter-efficient and computation-efficient way. Moreover, an attention module is introduced to further boost our network’s performance. We denote our network as SparseNet. We evaluate SparseNet on datasets of CIFAR(including CIFAR10 and CIFAR100) and SVHN. Experiments show that SparseNet can obtain improvements over the state-of-the-art on CIFAR10 and SVHN. Furthermore, while achieving comparable performances as DenseNet on these datasets, SparseNet is x2.6 smaller and x3.7 faster than the original DenseNet. |
| Sparseout | Dropout is commonly used to help reduce overfitting in deep neural networks. Sparsity is a potentially important property of neural networks, but is not explicitly controlled by Dropout-based regularization. In this work, we propose Sparseout a simple and efficient variant of Dropout that can be used to control the sparsity of the activations in a neural network. We theoretically prove that Sparseout is equivalent to an $L_q$ penalty on the features of a generalized linear model and that Dropout is a special case of Sparseout for neural networks. We empirically demonstrate that Sparseout is computationally inexpensive and is able to control the desired level of sparsity in the activations. We evaluated Sparseout on image classification and language modelling tasks to see the effect of sparsity on these tasks. We found that sparsity of the activations is favorable for language modelling performance while image classification benefits from denser activations. Sparseout provides a way to investigate sparsity in state-of-the-art deep learning models. Source code for Sparseout could be found at \url{https://…/sparseout}. |
| SparseStep Regression | The SparseStep algorithm is presented for the estimation of a sparse parameter vector in the linear regression problem. The algorithm works by adding an approximation of the exact counting norm as a constraint on the model parameters and iteratively strengthening this approximation to arrive at a sparse solution. Theoretical analysis of the penalty function shows that the estimator yields unbiased estimates of the parameter vector. An iterative majorization algorithm is derived which has a straightforward implementation reminiscent of ridge regression. In addition, the SparseStep algorithm is compared with similar methods through a rigorous simulation study which shows it often outperforms existing methods in both model fit and prediction accuracy. sparsestep |
| Sparsified Capsule Network | Capsule network has shown various advantages over convolutional neural network (CNN). It keeps more precise spatial information than CNN and uses equivariance instead of invariance during inference and highly potential to be a new effective tool for visual tasks. However, the current capsule networks have incompatible performance with CNN when facing datasets with background and complex target objects and are lacking in universal and efficient regularization method. We analyze the main reason of the incompatible performance as the conflict between information sensitiveness of capsule network and unreasonably higher activation value distribution of capsules in primary capsule layer. Correspondingly, we propose sparsified capsule network by sparsifying and restraining the activation value of capsules in primary capsule layer to suppress non-informative capsules and highlight discriminative capsules. In the experiments, the sparsified capsule network has achieved better performances on various mainstream datasets. In addition, the proposed sparsifying methods can be seen as a suitable, simple and efficient regularization method that can be generally used in capsule network. |
| Sparsity Oriented Importance Learning (SOIL) |
Sparsity Oriented Importance Learning (SOIL) provides an objective and informative profile of variable importances for high dimensional regression and classification models. SOIL |
| Sparsity-Aware Normalized Subband Adaptive Filter | We propose two sparsity-aware normalized subband adaptive filter (NSAF) algorithms by using the gradient descent method to minimize a combination of the original NSAF cost function and the l1-norm penalty function on the filter coefficients. This l1-norm penalty exploits the sparsity of a system in the coefficients update formulation, thus improving the performance when identifying sparse systems. Compared with prior work, the proposed algorithms have lower computational complexity with comparable performance. We study and devise statistical models for these sparsity-aware NSAF algorithms in the mean square sense involving their transient and steady -state behaviors. This study relies on the vectorization argument and the paraunitary assumption imposed on the analysis filter banks, and thus does not restrict the input signal to being Gaussian or having another distribution. In addition, we propose to adjust adaptively the intensity parameter of the sparsity attraction term. Finally, simulation results in sparse system identification demonstrate the effectiveness of our theoretical results. |
| Spartan Network | Deep learning models are vulnerable to adversarial examples which are input samples modified in order to maximize the error on the system. We introduce Spartan Networks, resistant deep neural networks that do not require input preprocessing nor adversarial training. These networks have an adversarial layer designed to discard some information of the network, thus forcing the system to focus on relevant input. This is done using a new activation function to discard data. The added layer trains the neural network to filter-out usually-irrelevant parts of its input. Our performance evaluation shows that Spartan Networks have a slightly lower precision but report a higher robustness under attack when compared to unprotected models. Results of this study of Adversarial AI as a new attack vector are based on tests conducted on the MNIST dataset. |
| Spatial | A high-level language for programming accelerators (FPGA). |
| Spatial Attenuation Context Network (SAC-Net) |
This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects. Our key idea is to adaptively propagate and aggregate the image context with variable attenuation over the entire feature maps. To achieve this, we design the spatial attenuation context (SAC) module to recurrently translate and aggregate the context features independently with different attenuation factors and then attentively learn the weights to adaptively integrate the aggregated context features. By further embedding the module to process individual layers in a deep network, namely SAC-Net, we can train the network end-to-end and optimize the context features for detecting salient objects. Compared with 22 state-of-the-art methods, experimental results show that our method performs favorably over all the others on six common benchmark data, both quantitatively and visually. |
| Spatial Broadcast Decoder | We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) the latent vector across space, concatenate fixed X- and Y-‘coordinate’ channels, and apply a fully convolutional network with 1×1 stride. This provides an architectural prior for dissociating positional from non-positional features in the latent distribution of VAEs, yet without providing any explicit supervision to this effect. We show that this architecture, which we term the Spatial Broadcast decoder, improves disentangling, reconstruction accuracy, and generalization to held-out regions in data space. It provides a particularly dramatic benefit when applied to datasets with small objects. We also emphasize a method for visualizing learned latent spaces that helped us diagnose our models and may prove useful for others aiming to assess data representations. Finally, we show the Spatial Broadcast Decoder is complementary to state-of-the-art (SOTA) disentangling techniques and when incorporated improves their performance. |
| Spatial Feature Extractor (SFE) |
Directly learning features from the point cloud has become an active research direction in 3D understanding. Existing learning-based methods usually construct local regions from the point cloud and extract the corresponding features using shared Multi-Layer Perceptron (MLP) and max pooling. However, most of these processes do not adequately take the spatial distribution of the point cloud into account, limiting the ability to perceive fine-grained patterns. We design a novel Local Spatial Attention (LSA) module to adaptively generate attention maps according to the spatial distribution of local regions. The feature learning process which integrates with these attention maps can effectively capture the local geometric structure. We further propose the Spatial Feature Extractor (SFE), which constructs a branch architecture, to aggregate the spatial information with associated features in each layer of the network better.The experiments show that our network, named LSANet, can achieve on par or better performance than the state-of-the-art methods when evaluating on the challenging benchmark datasets. The source code is available at https://…/LSANet. |
| Spatial Position Model | SpatialPosition |
| Spatial Random Sampling (SRS) |
Random column sampling is not guaranteed to yield data sketches that preserve the underlying structures of the data and may not sample sufficiently from less-populated data clusters. Also, adaptive sampling can often provide accurate low rank approximations, yet may fall short of producing descriptive data sketches, especially when the cluster centers are linearly dependent. Motivated by that, this paper introduces a novel randomized column sampling tool dubbed Spatial Random Sampling (SRS), in which data points are sampled based on their proximity to randomly sampled points on the unit sphere. The most compelling feature of SRS is that the corresponding probability of sampling from a given data cluster is proportional to the surface area the cluster occupies on the unit sphere, independently from the size of the cluster population. Although it is fully randomized, SRS is shown to provide descriptive and balanced data representations. The proposed idea addresses a pressing need in data science and holds potential to inspire many novel approaches for analysis of big data. |
| Spatial Sign Correlation | A new robust correlation estimator based on the spatial sign covariance matrix (SSCM) is proposed. We derive its asymptotic distribution and influence function at elliptical distributions. Finite sample and robustness properties are studied and compared to other robust correlation estimators by means of numerical simulations. sscor |
| Spatial Sign Covariance Matrix (SSCM) |
The robust estimation of multivariate location and shape is one of the most challenging problems in statistics and crucial in many application areas. The objective is to find highly efficient, robust, computable and affine equivariant location and covariance matrix estimates. In this paper three different concepts of multivariate sign and rank are considered and their ability to carry information about the geometry of the underlying distribution (or data cloud) are discussed. New techniques for robust covariance matrix estimation based on different sign and rank concepts are proposed and algorithms for computing them outlined. In addition, new tools for evaluating the qualitative and quantitative robustness of a covariance estimator are proposed. The use of these tools is demonstrated on two rank based covariance matrix estimates. Finally, to illustrate the practical importance of the problem, a signal processing example where robust covariance matrix estimates are needed is given. The Spatial Sign Covariance Matrix With Unknown Location ➘ “Spatial Sign Correlation” sscor |
| Spatial Simulated Annealing (SSA) |
Spatial simulated annealing uses slight perturbations of previous sampling designs and a random search technique to solve spatial optimization problems. Candidate measurement locations are iteratively moved around and optimized by minimizing the mean universal kriging variance. The approach relies on a known, pre-specified model for underlying spatial variation. ➚ “Simulated Annealing” spsann |
| Spatial Statistics | Spatial analysis or spatial statistics includes any of the formal techniques which study entities using their topological, geometric, or geographic properties. The phrase properly refers to a variety of techniques, many still in their early development, using different analytic approaches and applied in fields as diverse as astronomy, with its studies of the placement of galaxies in the cosmos, to chip fabrication engineering, with its use of ‘place and route’ algorithms to build complex wiring structures. The phrase is often used in a more restricted sense to describe techniques applied to structures at the human scale, most notably in the analysis of geographic data. The phrase is even sometimes used to refer to a specific technique in a single area of research, for example, to describe geostatistics. |
| Spatial Stochastic Frontier Analysis (SSFA) |
Spatial Stochastic Frontier Analysis (SSFA) is an original method for controlling the spatial heterogeneity in Stochastic Frontier Analysis (SFA) models by splitting the inefficiency term into three terms: the first one related to spatial peculiarities of the territory in which each single unit operates, the second one related to the specific production features and the third one representing the error term. ➘ “Stochastic Frontier Analysis” ssfa,spfrontier |
| Spatial Transformer GAN | We address the problem of finding realistic geometric corrections to a foreground object such that it appears natural when composited into a background image. To achieve this, we propose a novel Generative Adversarial Network (GAN) architecture that utilizes Spatial Transformer Networks (STNs) as the generator, which we call Spatial Transformer GANs (ST-GANs). ST-GANs seek image realism by operating in the geometric warp parameter space. In particular, we exploit an iterative STN warping scheme and propose a sequential training strategy that achieves better results compared to naive training of a single generator. One of the key advantages of ST-GAN is its applicability to high-resolution images indirectly since the predicted warp parameters are transferable between reference frames. We demonstrate our approach in two applications: (1) visualizing how indoor furniture (e.g. from product images) might be perceived in a room, (2) hallucinating how accessories like glasses would look when matched with real portraits. |
| Spatial Transformer Introspective Neural Network (ST-INN) |
Natural images contain many variations such as illumination differences, affine transformations, and shape distortions. Correctly classifying these variations poses a long standing problem. The most commonly adopted solution is to build large-scale datasets that contain objects under different variations. However, this approach is not ideal since it is computationally expensive and it is hard to cover all variations in one single dataset. Towards addressing this difficulty, we propose the spatial transformer introspective neural network (ST-INN) that explicitly generates samples with the unseen affine transformation variations in the training set. Experimental results indicate ST-INN achieves classification accuracy improvements on several benchmark datasets, including MNIST, affNIST, SVHN and CIFAR-10. We further extend our method to cross dataset classification tasks and few-shot learning problems to verify our method under extreme conditions and observe substantial improvements from experiment results. |
| Spatial Transformer Network (STN) |
Robotic grasp detection task is still challenging, particularly for novel objects. With the recent advance of deep learning, there have been several works on detecting robotic grasp using neural networks. Typically, regression based grasp detection methods have outperformed classification based detection methods in computation complexity with excellent accuracy. However, classification based robotic grasp detection still seems to have merits such as intermediate step observability and straightforward back propagation routine for end-to-end training. In this work, we propose a novel classification based robotic grasp detection method with multiple-stage spatial transformer networks (STN). Our proposed method was able to achieve state-of-the-art performance in accuracy with real- time computation. Additionally, unlike other regression based grasp detection methods, our proposed method allows partial observation for intermediate results such as grasp location and orientation for a number of grasp configuration candidates. |
| Spatially Coherent Randomized Attention Map (SCRAM) |
Attention mechanisms and non-local mean operations in general are key ingredients in many state-of-the-art deep learning techniques. In particular, the Transformer model based on multi-head self-attention has recently achieved great success in natural language processing and computer vision. However, the vanilla algorithm computing the Transformer of an image with n pixels has O(n^2) complexity, which is often painfully slow and sometimes prohibitively expensive for large-scale image data. In this paper, we propose a fast randomized algorithm — SCRAM — that only requires O(n log(n)) time to produce an image attention map. Such a dramatic acceleration is attributed to our insight that attention maps on real-world images usually exhibit (1) spatial coherence and (2) sparse structure. The central idea of SCRAM is to employ PatchMatch, a randomized correspondence algorithm, to quickly pinpoint the most compatible key (argmax) for each query first, and then exploit that knowledge to design a sparse approximation to non-local mean operations. Using the argmax (mode) to dynamically construct the sparse approximation distinguishes our algorithm from all of the existing sparse approximate methods and makes it very efficient. Moreover, SCRAM is a broadly applicable approximation to any non-local mean layer in contrast to some other sparse approximations that can only approximate self-attention. Our preliminary experimental results suggest that SCRAM is indeed promising for speeding up or scaling up the computation of attention maps in the Transformer. |
| Spatially Compact Semantic Scan (SCSS) |
Many methods have been proposed for detecting emerging events in text streams using topic modeling. However, these methods have shortcomings that make them unsuitable for rapid detection of locally emerging events on massive text streams. We describe Spatially Compact Semantic Scan (SCSS) that has been developed specifically to overcome the shortcomings of current methods in detecting new spatially compact events in text streams. SCSS employs alternating optimization between using semantic scan to estimate contrastive foreground topics in documents, and discovering spatial neighborhoods with high occurrence of documents containing the foreground topics. We evaluate our method on Emergency Department chief complaints dataset (ED dataset) to verify the effectiveness of our method in detecting real-world disease outbreaks from free-text ED chief complaint data. |
| SPAtially Related Convolutional Neural Network (SPARCNN) |
The ability to accurately detect and classify objects at varying pixel sizes in cluttered scenes is crucial to many Navy applications. However, detection performance of existing state-of the-art approaches such as convolutional neural networks (CNNs) degrade and suffer when applied to such cluttered and multi-object detection tasks. We conjecture that spatial relationships between objects in an image could be exploited to significantly improve detection accuracy, an approach that had not yet been considered by any existing techniques (to the best of our knowledge) at the time the research was conducted. We introduce a detection and classification technique called Spatially Related Detection with Convolutional Neural Networks (SPARCNN) that learns and exploits a probabilistic representation of inter-object spatial configurations within images from training sets for more effective region proposals to use with state-of-the-art CNNs. Our empirical evaluation of SPARCNN on the VOC 2007 dataset shows that it increases classification accuracy by 8% when compared to a region proposal technique that does not exploit spatial relations. More importantly, we obtained a higher performance boost of 18.8% when task difficulty in the test set is increased by including highly obscured objects and increased image clutter. |
| Spatially-Preserved Doubly-Injected Object Detection CNN (S-DOD-CNN) |
We present a novel event recognition approach called Spatially-preserved Doubly-injected Object Detection CNN (S-DOD-CNN), which incorporates the spatially preserved object detection information in both a direct and an indirect way. Indirect injection is carried out by simply sharing the weights between the object detection modules and the event recognition module. Meanwhile, our novelty lies in the fact that we have preserved the spatial information for the direct injection. Once multiple regions-of-intereset (RoIs) are acquired, their feature maps are computed and then projected onto a spatially-preserving combined feature map using one of the four RoI Projection approaches we present. In our architecture, combined feature maps are generated for object detection which are directly injected to the event recognition module. Our method provides the state-of-the-art accuracy for malicious event recognition. |
| Spatially-Weighted Anomaly Detection Method (SPADE) |
Many types of anomaly detection methods have been proposed recently, and applied to a wide variety of fields including medical screening and production quality checking. Some methods have utilized images, and, in some cases, a part of the anomaly images is known beforehand. However, this kind of information is dismissed by previous methods, because the methods can only utilize a normal pattern. Moreover, the previous methods suffer a decrease in accuracy due to negative effects from surrounding noises. In this study, we propose a spatially-weighted anomaly detection method (SPADE) that utilizes all of the known patterns and lessens the vulnerability to ambient noises by applying Grad-CAM, which is the visualization method of a CNN. We evaluated our method quantitatively using two datasets, the MNIST dataset with noise and a dataset based on a brief screening test for dementia. |
| Spatial-Spectral Manifold Reconstruction Preserving Embedding (SSMRPE) |
The graph embedding (GE) methods have been widely applied for dimensionality reduction of hyperspectral imagery (HSI). However, a major challenge of GE is how to choose proper neighbors for graph construction and explore the spatial information of HSI data. In this paper, we proposed an unsupervised dimensionality reduction algorithm termed spatial-spectral manifold reconstruction preserving embedding (SSMRPE) for HSI classification. At first, a weighted mean filter (WMF) is employed to preprocess the image, which aims to reduce the influence of background noise. According to the spatial consistency property of HSI, the SSMRPE method utilizes a new spatial-spectral combined distance (SSCD) to fuse the spatial structure and spectral information for selecting effective spatial-spectral neighbors of HSI pixels. Then, it explores the spatial relationship between each point and its neighbors to adjusts the reconstruction weights for improving the efficiency of manifold reconstruction. As a result, the proposed method can extract the discriminant features and subsequently improve the classification performance of HSI. The experimental results on PaviaU and Salinas hyperspectral datasets indicate that SSMRPE can achieve better classification accuracies in comparison with some state-of-the-art methods. |
| Spatial-Temporal-Spectral Framework Based on a Deep Convolutional Neural Network (STS-CNN) |
Because of the internal malfunction of satellite sensors and poor atmospheric conditions such as thick cloud, the acquired remote sensing data often suffer from missing information, i.e., the data usability is greatly reduced. In this paper, a novel method of missing information reconstruction in remote sensing images is proposed. The unified spatial-temporal-spectral framework based on a deep convolutional neural network (STS-CNN) employs a unified deep convolutional neural network combined with spatial-temporal-spectral supplementary information. In addition, to address the fact that most methods can only deal with a single missing information reconstruction task, the proposed approach can solve three typical missing information reconstruction tasks: 1) dead lines in Aqua MODIS band 6; 2) the Landsat ETM+ Scan Line Corrector (SLC)-off problem; and 3) thick cloud removal. It should be noted that the proposed model can use multi-source data (spatial, spectral, and temporal) as the input of the unified framework. The results of both simulated and real-data experiments demonstrate that the proposed model exhibits high effectiveness in the three missing information reconstruction tasks listed above. |
| Spatio-Temporal Deep Graph Infomax (STDGI) |
Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce Spatio-Temporal Deep Graph Infomax (STDGI)—a fully unsupervised node representation learning approach based on mutual information maximization that exploits both the temporal and spatial dynamics of the graph. Our model tackles the challenging task of node-level regression by training embeddings to maximize the mutual information between patches of the graph, at any given time step, and between features of the central nodes of patches, in the future. We demonstrate through experiments and qualitative studies that the learned representations can successfully encode relevant information about the input graph and improve the predictive performance of spatio-temporal auto-regressive forecasting models. |
| Spatio-TEmporal Fuzzy neural Network (STEF-Net) |
In spite of its importance, passenger demand prediction is a highly challenging problem, because the demand is simultaneously influenced by the complex interactions among many spatial and temporal factors and other external factors such as weather. To address this problem, we propose a Spatio-TEmporal Fuzzy neural Network (STEF-Net) to accurately predict passenger demands incorporating the complex interactions of all known important factors. We design an end-to-end learning framework with different neural networks modeling different factors. Specifically, we propose to capture spatio-temporal feature interactions via a convolutional long short-term memory network and model external factors via a fuzzy neural network that handles data uncertainty significantly better than deterministic methods. To keep the temporal relations when fusing two networks and emphasize discriminative spatio-temporal feature interactions, we employ a novel feature fusion method with a convolution operation and an attention layer. As far as we know, our work is the first to fuse a deep recurrent neural network and a fuzzy neural network to model complex spatial-temporal feature interactions with additional uncertain input features for predictive learning. Experiments on a large-scale real-world dataset show that our model achieves more than 10% improvement over the state-of-the-art approaches. |
| Spatiotemporal Intrinsic Mode Decomposition (STIMD) |
We propose a new solution to the blind source separation problem that factors mixed time-series signals into a sum of spatiotemporal modes, with the constraint that the temporal components are intrinsic mode functions (IMF’s). The key motivation is that IMF’s allow the computation of meaningful Hilbert transforms of non-stationary data, from which instantaneous time-frequency representations may be derived. Our spatiotemporal intrinsic mode decomposition (STIMD) method leverages spatial correlations to generalize the extraction of IMF’s from one-dimensional signals, commonly performed using the empirical mode decomposition (EMD), to multi-dimensional signals. Further, this data-driven method enables future-state prediction. We demonstrate STIMD on several synthetic examples, comparing it to common matrix factorization techniques, namely singular value decomposition (SVD), independent component analysis (ICA), and dynamic mode decomposition (DMD). We show that STIMD outperforms these methods at reconstruction and extracting interpretable modes. Next, we apply STIMD to analyze two real-world datasets, gravitational wave data and neural recordings from the rodent hippocampus. |
| Spatio-Temporal Neural Network (ST-NN) |
In this paper, we develop a reinforcement learning (RL) based system to learn an effective policy for carpooling that maximizes transportation efficiency so that fewer cars are required to fulfill the given amount of trip demand. For this purpose, first, we develop a deep neural network model, called ST-NN (Spatio-Temporal Neural Network), to predict taxi trip time from the raw GPS trip data. Secondly, we develop a carpooling simulation environment for RL training, with the output of ST-NN and using the NYC taxi trip dataset. In order to maximize transportation efficiency and minimize traffic congestion, we choose the effective distance covered by the driver on a carpool trip as the reward. Therefore, the more effective distance a driver achieves over a trip (i.e. to satisfy more trip demand) the higher the efficiency and the less will be the traffic congestion. We compared the performance of RL learned policy to a fixed policy (which always accepts carpool) as a baseline and obtained promising results that are interpretable and demonstrate the advantage of our RL approach. We also compare the performance of ST-NN to that of state-of-the-art travel time estimation methods and observe that ST-NN significantly improves the prediction performance and is more robust to outliers. |
| Spatio-Temporal U-Network (ST-UNet) |
The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is crucial, e.g. traffic networks and financial transaction graphs. Despite the constant progress made on learning structured data, there is still a lack of effective means to extract dynamic complex features from spatio-temporal structures. Particularly, conventional models such as convolutional networks or recurrent neural networks are incapable of revealing the temporal patterns in short or long terms and exploring the spatial properties in local or global scope from spatio-temporal graphs simultaneously. To tackle this problem, we design a novel multi-scale architecture, Spatio-Temporal U-Net (ST-UNet), for graph-structured time series modeling. In this U-shaped network, a paired sampling operation is proposed in spacetime domain accordingly: the pooling (ST-Pool) coarsens the input graph in spatial from its deterministic partition while abstracts multi-resolution temporal dependencies through dilated recurrent skip connections; based on previous settings in the downsampling, the unpooling (ST-Unpool) restores the original structure of spatio-temporal graphs and resumes regular intervals within graph sequences. Experiments on spatio-temporal prediction tasks demonstrate that our model effectively captures comprehensive features in multiple scales and achieves substantial improvements over mainstream methods on several real-world datasets. |
| spatstat | spatstat is an R package for spatial statistics with a strong focus on analysing spatial point patterns in 2D (with some support for 3D and very basic support for space-time). |
| SPCALDA | A new reduced-rank LDA method which works for high dimensional multi-class data. |
| SpCoSLAM 2.0 | In this paper, we propose a novel online learning algorithm, SpCoSLAM 2.0 for spatial concepts and lexical acquisition with higher accuracy and scalability. In previous work, we proposed SpCoSLAM as an online learning algorithm based on the Rao–Blackwellized particle filter. However, this conventional algorithm had problems such as the decrease of the estimation accuracy due to the influence of the early stages of learning as well as the increase of the computational complexity with the increase of the training data. Therefore, we first develop an improved algorithm by introducing new techniques such as rejuvenation. Next, we develop a scalable algorithm to reduce the calculation time while maintaining a higher accuracy than the conventional algorithm. In the experiment, we evaluate and compare the estimation accuracy and calculation time of the proposed algorithm, conventional online algorithm, and batch learning. The experimental results demonstrate that the proposed algorithm not only exceeds the accuracy of the conventional algorithm but also capable of achieving an accuracy comparable to that of batch learning. In addition, the proposed algorithm showed that the calculation time does not depend on the amount of training data and becomes constant for each step with the scalable algorithm. |
| Speaker Diarisation | Speaker diarisation (or diarization) is the process of partitioning an input audio stream into homogeneous segments according to the speaker identity. It can enhance the readability of an automatic speech transcription by structuring the audio stream into speaker turns and, when used together with speaker recognition systems, by providing the speaker’s true identity. It is used to answer the question ‘who spoke when?’ Speaker diarisation is a combination of speaker segmentation and speaker clustering. The first aims at finding speaker change points in an audio stream. The second aims at grouping together speech segments on the basis of speaker characteristics. |
| SpecAugment | We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment on Listen, Attend and Spell networks for end-to-end speech recognition tasks. We achieve state-of-the-art performance on the LibriSpeech 960h and Swichboard 300h tasks, outperforming all prior work. On LibriSpeech, we achieve 6.8% WER on test-other without the use of a language model, and 5.8% WER with shallow fusion with a language model. This compares to the previous state-of-the-art hybrid system of 7.5% WER. For Switchboard, we achieve 7.2%/14.6% on the Switchboard/CallHome portion of the Hub5’00 test set without the use of a language model, and 6.8%/14.1% with shallow fusion, which compares to the previous state-of-the-art hybrid system at 8.3%/17.3% WER. |
| Specificity | Sensitivity and specificity are statistical measures of the performance of a binary classification test, also known in statistics as classification function. Sensitivity (also called the true positive rate, or the recall rate in some fields) measures the proportion of actual positives which are correctly identified as such (e.g. the percentage of sick people who are correctly identified as having the condition). Specificity (sometimes called the true negative rate) measures the proportion of negatives which are correctly identified as such (e.g. the percentage of healthy people who are correctly identified as not having the condition). These two measures are closely related to the concepts of type I and type II errors. A perfect predictor would be described as 100% sensitive (i.e. predicting all people from the sick group as sick) and 100% specific (i.e. not predicting anyone from the healthy group as sick); however, theoretically any predictor will possess a minimum error bound known as the Bayes error rate. |
| Spectral Clustering | In multivariate statistics and the clustering of data, spectral clustering techniques make use of the spectrum (eigenvalues) of the similarity matrix of the data to perform dimensionality reduction before clustering in fewer dimensions. The similarity matrix is provided as an input and consists of a quantitative assessment of the relative similarity of each pair of points in the dataset. In application to image segmentation, spectral clustering is known as segmentation-based object categorization. |
| Spectral Clustering using Deep Neural Networks (SpectralNet) |
Spectral clustering is a leading and popular technique in unsupervised data analysis. Two of its major limitations are scalability and generalization of the spectral embedding (i.e., out-of-sample-extension). In this paper we introduce a deep learning approach to spectral clustering that overcomes the above shortcomings. Our network, which we call SpectralNet, learns a map that embeds input data points into the eigenspace of their associated graph Laplacian matrix and subsequently clusters them. We train SpectralNet using a procedure that involves constrained stochastic optimization. Stochastic optimization allows it to scale to large datasets, while the constraints, which are implemented using a special-purpose output layer, allow us to keep the network output orthogonal. Moreover, the map learned by SpectralNet naturally generalizes the spectral embedding to unseen data points. To further improve the quality of the clustering, we replace the standard pairwise Gaussian affinities with affinities leaned from unlabeled data using a Siamese network. Additional improvement can be achieved by applying the network to code representations produced, e.g., by standard autoencoders. Our end-to-end learning procedure is fully unsupervised. In addition, we apply VC dimension theory to derive a lower bound on the size of SpectralNet. State-of-the-art clustering results are reported on the Reuters dataset. Our implementation is publicly available at https://…/SpectralNet . |
| Spectral Collaborative Filtering (SpectralCF) |
Despite the popularity of Collaborative Filtering (CF), CF-based methods are haunted by the \textit{cold-start} problem, which has a significantly negative impact on users’ experiences with Recommender Systems (RS). In this paper, to overcome the aforementioned drawback, we first formulate the relationships between users and items as a bipartite graph. Then, we propose a new spectral convolution operation directly performing in the \textit{spectral domain}, where not only the proximity information of a graph but also the connectivity information hidden in the graph are revealed. With the proposed spectral convolution operation, we build a deep recommendation model called Spectral Collaborative Filtering (SpectralCF). Benefiting from the rich information of connectivity existing in the \textit{spectral domain}, SpectralCF is capable of discovering deep connections between users and items and therefore, alleviates the \textit{cold-start} problem for CF. To the best of our knowledge, SpectralCF is the first CF-based method directly learning from the \textit{spectral domains} of user-item bipartite graphs. We apply our method on several standard datasets. It is shown that SpectralCF significantly outperforms state-of-the-art models. Code and data are available at \url{https://…/SpectralCF}. |
| Spectral Convolution Networks | Previous research has shown that computation of convolution in the frequency domain provides a significant speedup versus traditional convolution network implementations. However, this performance increase comes at the expense of repeatedly computing the transform and its inverse in order to apply other network operations such as activation, pooling, and dropout. We show, mathematically, how convolution and activation can both be implemented in the frequency domain using either the Fourier or Laplace transformation. The main contributions are a description of spectral activation under the Fourier transform and a further description of an efficient algorithm for computing both convolution and activation under the Laplace transform. By computing both the convolution and activation functions in the frequency domain, we can reduce the number of transforms required, as well as reducing overall complexity. Our description of a spectral activation function, together with existing spectral analogs of other network functions may then be used to compose a fully spectral implementation of a convolution network. |
| Spectral Graph Analysis | Complex networks or graphs are ubiquitous in sciences and engineering: biological networks, brain networks, transportation networks, social networks, and the World Wide Web, to name a few. Spectral graph theory provides a set of useful techniques and models for understanding `patterns of interconnectedness’ in a graph. Our prime focus in this paper is on the following question: Is there a unified explanation and description of the fundamental spectral graph methods? There are at least two reasons to be interested in this question. Firstly, to gain a much deeper and refined understanding of the basic foundational principles, and secondly, to derive rich consequences with practical significance for algorithm design. However, despite half a century of research, this question remains one of the most formidable open issues, if not the core problem in modern network science. The achievement of this paper is to take a step towards answering this question by discovering a simple, yet universal statistical logic of spectral graph analysis. The prescribed viewpoint appears to be good enough to accommodate almost all existing spectral graph techniques as a consequence of just one single formalism and algorithm. |
| Spectral Graph Clustering (SGC) |
➘ “Spectral Clustering” |
| Spectral Inference Network | We present Spectral Inference Networks, a framework for learning eigenfunctions of linear operators by stochastic optimization. Spectral Inference Networks generalize Slow Feature Analysis to generic symmetric operators, and are closely related to Variational Monte Carlo methods from computational physics. As such, they can be a powerful tool for unsupervised representation learning from video or pairs of data. We derive a training algorithm for Spectral Inference Networks that addresses the bias in the gradients due to finite batch size and allows for online learning of multiple eigenfunctions. We show results of training Spectral Inference Networks on problems in quantum mechanics and feature learning for videos on synthetic datasets as well as the Arcade Learning Environment. Our results demonstrate that Spectral Inference Networks accurately recover eigenfunctions of linear operators, can discover interpretable representations from video and find meaningful subgoals in reinforcement learning environments. |
| Spectral Normalization | One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discriminator. Our new normalization technique is computationally light and easy to incorporate into existing implementations. We tested the efficacy of spectral normalization on CIFAR10, STL-10, and ILSVRC2012 dataset, and we experimentally confirmed that spectrally normalized GANs (SN-GANs) is capable of generating images of better or equal quality relative to the previous training stabilization techniques. |
| Spectral Subspace Sparsification | We introduce a new approach to spectral sparsification that approximates the quadratic form of the pseudoinverse of a graph Laplacian restricted to a subspace. We show that sparsifiers with a near-linear number of edges in the dimension of the subspace exist. Our setting generalizes that of Schur complement sparsifiers. Our approach produces sparsifiers by sampling a uniformly random spanning tree of the input graph and using that tree to guide an edge elimination procedure that contracts, deletes, and reweights edges. In the context of Schur complement sparsifiers, our approach has two benefits over prior work. First, it produces a sparsifier in almost-linear time with no runtime dependence on the desired error. We directly exploit this to compute approximate effective resistances for a small set of vertex pairs in faster time than prior work (Durfee-Kyng-Peebles-Rao-Sachdeva ’17). Secondly, it yields sparsifiers that are reweighted minors of the input graph. As a result, we give a near-optimal answer to a variant of the Steiner point removal problem. A key ingredient of our algorithm is a subroutine of independent interest: a near-linear time algorithm that, given a chosen set of vertices, builds a data structure from which we can query a multiplicative approximation to the decrease in the effective resistance between two vertices after identifying all vertices in the chosen set to a single vertex with inverse polynomial additional additive error in near-constant time. |
| Spectral-Pruning | The model size of deep neural network is getting larger and larger to realize superior performance in complicated tasks. This makes it difficult to implement deep neural network in small edge-computing devices. To overcome this problem, model compression methods have been gathering much attention. However, there have been only few theoretical back-grounds that explain what kind of quantity determines the compression ability. To resolve this issue, we develop a new theoretical frame-work for model compression, and propose a new method called {\it Spectral-Pruning} based on the theory. Our theoretical analysis is based on the observation such that the eigenvalues of the covariance matrix of the output from nodes in the internal layers often shows rapid decay. We define ‘degree of freedom’ to quantify an intrinsic dimensionality of the model by using the eigenvalue distribution and show that the compression ability is essentially controlled by this quantity. Along with this, we give a generalization error bound of the compressed model. Our proposed method is applicable to wide range of models, unlike the existing methods, e.g., ones possess complicated branches as implemented in SegNet and ResNet. Our method makes use of both ‘input’ and ‘output’ in each layer and is easy to implement. We apply our method to several datasets to justify our theoretical analyses and show that the proposed method achieves the state-of-the-art performance. |
| SPECTRE | Network alignment consists of finding a correspondence between the nodes of two networks. From aligning proteins in computational biology, to de-anonymization of social networks, to recognition tasks in computer vision, this problem has applications in many diverse areas. The current approaches to network alignment mostly focus on the case where prior information is available, either in the form of a seed set of correctly-matched nodes or attributes on the nodes and/or edges. Moreover, those approaches which assume no such prior information tend to be computationally expensive and do not scale to large-scale networks. However, many real-world networks are very large in size, and prior information can be expensive, if not impossible, to obtain. In this paper we introduce SPECTRE, a scalable, accurate algorithm able to solve the network alignment problem with no prior information. SPECTRE makes use of spectral centrality measures and percolation techniques to robustly align nodes across networks, even if those networks exhibit only moderate correlation. Through extensive numerical experiments, we show that SPECTRE is able to recover high-accuracy alignments on both synthetic and real-world networks, and outperforms other algorithms in the seedless case. |
| Spectrum Anomaly Detector with Interpretable FEatures (SAIFE) |
Detecting anomalous behavior in wireless spectrum is a demanding task due to the sheer complexity of the electromagnetic spectrum use. Wireless spectrum anomalies can take a wide range of forms from the presence of an unwanted signal in a licensed band to the absence of an expected signal, which makes manual labeling of anomalies difficult and suboptimal. We present, Spectrum Anomaly Detector with Interpretable FEatures (SAIFE), an Adversarial Autoencoder (AAE) based anomaly detector for wireless spectrum anomaly detection using Power Spectral Density (PSD) data which achieves good anomaly detection and localization in an unsupervised setting. In addition, we investigate the model’s capabilities to learn interpretable features such as signal bandwidth, class and center frequency in a semi-supervised fashion. Along with anomaly detection the model exhibits promising results for lossy PSD data compression up to 120X and semisupervised signal classification accuracy close to 100% on three datasets just using 20% labeled samples. Finally the model is tested on data from one of the distributed Electrosense sensors over a long term of 500 hours showing its anomaly detection capabilities. |
| Speculative Query Planning (Spec-QP) |
Organisations store huge amounts of data from multiple heterogeneous sources in the form of Knowledge Graphs (KGs). One of the ways to query these KGs is to use SPARQL queries over a database engine. Since SPARQL follows exact match semantics, the queries may return too few or no results. Recent works have proposed query relaxation where the query engine judiciously replaces a query predicate with similar predicates using weighted relaxation rules mined from the KG. The space of possible relaxations is potentially too large to fully explore and users are typically interested in only top-k results, so such query engines use top-k algorithms for query processing. However, they may still process all the relaxations, many of whose answers do not contribute towards top-k answers. This leads to computation overheads and delayed response times. We propose Spec-QP, a query planning framework that speculatively determines which relaxations will have their results in the top-k answers. Only these relaxations are processed using the top-k operators. We, therefore, reduce the computation overheads and achieve faster response times without adversely affecting the quality of results. We tested Spec-QP over two datasets – XKG and Twitter, to demonstrate the efficiency of our planning framework at reducing runtimes with reasonable accuracy for query engines supporting relaxations. |
| Speech Analytics | Speech analytics is the process of analyzing recorded calls to gather information, brings structure to customer interactions and exposes information buried in customer contact center interactions with an enterprise. Although it often includes elements of automatic speech recognition, where the identities of spoken words or phrases are determined, it may also include analysis of one or more of the following: the topic(s) being discussed the emotional character of the speech the amount and locations of speech versus non-speech (e.g. call hold time or periods of silence) One use of speech analytics applications is to spot spoken keywords or phrases, either as real-time alerts on live audio or as a post-processing step on recorded speech. This technique is also known as audio mining. Other uses include categorization of speech, for example in the contact center environment, to identify calls from unsatisfied customers. Speech analytics in contact centers can be used to extract critical business intelligence that would otherwise be lost. By analyzing and categorizing recorded phone conversations between companies and their customers, useful information can be discovered relating to strategy, product, process, operational issues and contact center agent performance. This information gives decision-makers insight into what customers really think about their company so that they can quickly react. In addition, speech analytics can automatically identify areas in which contact center agents may need additional training or coaching, and can automatically monitor the customer service provided on calls. |
| Speech2Vec | In this paper, we propose a novel deep neural network architecture, Speech2Vec, for learning fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to the underlying spoken words, and are close to other vectors in the embedding space if their corresponding underlying spoken words are semantically similar. The proposed model can be viewed as a speech version of Word2Vec. Its design is based on a RNN Encoder-Decoder framework, and borrows the methodology of skipgrams or continuous bag-of-words for training. Learning word embeddings directly from speech enables Speech2Vec to make use of the semantic information carried by speech that does not exist in plain text. The learned word embeddings are evaluated and analyzed on 13 widely used word similarity benchmarks, and outperform word embeddings learned by Word2Vec from the transcriptions. |
| Speed as a Supervisor (SaaS) |
We introduce the SaaS Algorithm for semi-supervised learning, which uses learning speed during stochastic gradient descent in a deep neural network to measure the quality of an iterative estimate of the posterior probability of unknown labels. Training speed in supervised learning correlates strongly with the percentage of correct labels, so we use it as an inference criterion for the unknown labels, without attempting to infer the model parameters at first. Despite its simplicity, SaaS achieves state-of-the-art results in semi-supervised learning benchmarks. |
| SpeedReader | Most popular web browsers include ‘reader modes’ that improve the user experience by removing un-useful page elements. Reader modes reformat the page to hide elements that are not related to the page’s main content. Such page elements include site navigation, advertising related videos and images, and most JavaScript. The intended end result is that users can enjoy the content they are interested in, without distraction. In this work, we consider whether the ‘reader mode’ can be widened to also provide performance and privacy improvements. Instead of its use as a post-render feature to clean up the clutter on a page we propose SpeedReader as an alternative multistep pipeline that is part of the rendering pipeline. Once the tool decides during the initial phase of a page load that a page is suitable for reader mode use, it directly applies document tree translation before the page is rendered. Based on our measurements, we believe that SpeedReader can be continuously enabled in order to drastically improve end-user experience, especially on slower mobile connections. Combined with our approach to predicting which pages should be rendered in reader mode with 91% accuracy, it achieves drastic speedups and bandwidth reductions of up to 27x and 84x respectively on average. We further find that our novel ‘reader mode’ approach brings with it significant privacy improvements to users. Our approach effectively removes all commonly recognized trackers, issuing 115 fewer requests to third parties, and interacts with 64 fewer trackers on average, on transformed pages. |
| SPFlow | We introduce SPFlow, an open-source Python library providing a simple interface to inference, learning and manipulation routines for deep and tractable probabilistic models called Sum-Product Networks (SPNs). The library allows one to quickly create SPNs both from data and through a domain specific language (DSL). It efficiently implements several probabilistic inference routines like computing marginals, conditionals and (approximate) most probable explanations (MPEs) along with sampling as well as utilities for serializing, plotting and structure statistics on an SPN. Moreover, many of the algorithms proposed in the literature to learn the structure and parameters of SPNs are readily available in SPFlow. Furthermore, SPFlow is extremely extensible and customizable, allowing users to promptly distill new inference and learning routines by injecting custom code into a lightweight functional-oriented API framework. This is achieved in SPFlow by keeping an internal Python representation of the graph structure that also enables practical compilation of an SPN into a TensorFlow graph, C, CUDA or FPGA custom code, significantly speeding-up computations. |
| Spherical Paragraph Model (SPM) |
Representing texts as fixed-length vectors is central to many language processing tasks. Most traditional methods build text representations based on the simple Bag-of-Words (BoW) representation, which loses the rich semantic relations between words. Recent advances in natural language processing have shown that semantically meaningful representations of words can be efficiently acquired by distributed models, making it possible to build text representations based on a better foundation called the Bag-of-Word-Embedding (BoWE) representation. However, existing text representation methods using BoWE often lack sound probabilistic foundations or cannot well capture the semantic relatedness encoded in word vectors. To address these problems, we introduce the Spherical Paragraph Model (SPM), a probabilistic generative model based on BoWE, for text representation. SPM has good probabilistic interpretability and can fully leverage the rich semantics of words, the word co-occurrence information as well as the corpus-wide information to help the representation learning of texts. Experimental results on topical classification and sentiment analysis demonstrate that SPM can achieve new state-of-the-art performances on several benchmark datasets. |
| Spherical Principal Component Analysis | Principal Component Analysis (PCA) is one of the most important methods to handle high dimensional data. However, most of the studies on PCA aim to minimize the loss after projection, which usually measures the Euclidean distance, though in some fields, angle distance is known to be more important and critical for analysis. In this paper, we propose a method by adding constraints on factors to unify the Euclidean distance and angle distance. However, due to the nonconvexity of the objective and constraints, the optimized solution is not easy to obtain. We propose an alternating linearized minimization method to solve it with provable convergence rate and guarantee. Experiments on synthetic data and real-world datasets have validated the effectiveness of our method and demonstrated its advantages over state-of-art clustering methods. |
| Spider | We present Spider, a large-scale, complex and cross-domain semantic parsing and text-to-SQL dataset annotated by 11 college students. It consists of 10,181 questions and 5,693 unique complex SQL queries on 200 databases with multiple tables, covering 138 different domains. We define a new complex and cross-domain semantic parsing and text-to-SQL task where different complex SQL queries and databases appear in train and test sets. In this way, the task requires the model to generalize well to both new SQL queries and new database schemas. Spider is distinct from most of the previous semantic parsing tasks because they all use a single database and the exact same programs in the train set and the test set. We experiment with various state-of-the-art models and the best model achieves only 14.3% exact matching accuracy on a database split setting. This shows that Spider presents a strong challenge for future research. Our dataset and task are publicly available at https://…/spider. |
| SpiderBoost | There has been extensive research on developing stochastic variance reduced methods to solve large-scale optimization problems. More recently, a novel algorithm of such a type named SPIDER has been developed in \cite{Fang2018}, which was shown to outperform existing algorithms of the same type and meet the lower bound in certain regimes. Though interesting in theory, SPIDER requires $\epsilon$-level stepsize to guarantee the convergence, and consequently runs slow in practice. This paper proposes SpiderBoost as an improved SPIDER scheme, which comes with two major advantages compared to SPIDER. First, it allows much larger stepsize without sacrificing the convergence rate, and hence runs substantially faster than SPIDER in practice. Second, it extends much more easily to proximal algorithms with guaranteed convergence for solving composite optimization problems, which appears challenging for SPIDER due to stringent requirement on per-iteration increment to guarantee its convergence. Both advantages can be attributed to the new convergence analysis we develop for SpiderBoost that allows much more flexibility for choosing algorithm parameters. As further generalization of SpiderBoost, we show that proximal SpiderBoost achieves a stochastic first-order oracle (SFO) complexity of $\mathcal{O}(\min\epsilon^{-1},\epsilon^{-3/2}\})$ for composite optimization, which improves the existing best results by a factor of $\mathcal{O}(\min,\epsilon^{-1/6}\})$. |
| SpiderCNN | Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we propose a novel convolutional architecture, termed SpiderCNN, to efficiently extract geometric features from point clouds. SpiderCNN is comprised of units called SpiderConv, which extend convolutional operations from regular grids to irregular point set that can be embedded in R^n, by parametrizing a family of convolutional filters. We elaborately design the filter as a product of simple step function that captures local geodesic information and a Taylor polynomial that ensures the expressiveness. SpiderCNN inherits the multi-scale hierarchical architecture from the classical CNNs, which allows it to extract semantic deep features. Experiments on ModelNet40 demonstrate that SpiderCNN achieves the-state-of-the art accuracy 92.4% on standard benchmarks, and shows competitive performance on segmentation task. |
| SPIGAN | Deep Learning for Computer Vision depends mainly on the source of supervision. Photo-realistic simulators can generate large-scale automatically labeled syntheticdata, but introduce a domain gap negatively impacting performance. We propose anew unsupervised domain adaptation algorithm, called SPIGAN, relying on Simulator Privileged Information (PI) and Generative Adversarial Networks (GAN). We use internal data from the simulator as PI during the training of a target tasknetwork. We experimentally evaluate our approach on semantic segmentation. We train the networks on real-world Cityscapes and Vistas datasets, using only unlabeled real-world images and synthetic labeled data with z-buffer (depth) PI fromthe SYNTHIA dataset. Our method improves over no adaptation and state-of-the-art unsupervised domain adaptation techniques. |
| SPIKE | Maintaining web-services is a mission-critical task. Any downtime of web-based services means loss of revenue. Worse, such downtimes can damage the reputation of an organization as a reliable service provider (and in the current competitive web services market, such a loss of reputation causes extensive loss of future revenue). To address this issue, we developed SPIKE, a data mining tool which can predict upcoming service breakdowns, half an hour into the future. Such predictions let an organization alert and assemble the tiger team to address the problem (e.g. by reconfiguring cloud hardware in order to reduce the likelihood of that breakdown). SPIKE utilizes (a) regression tree learning (with CART); (b) synthetic minority over-sampling (to handle how rare spikes are in our data); (c) hyperparameter optimization (to learn best settings for our local data) and (d) a technique we called ‘topology sampling’ where training vectors are built from extensive details of an individual node plus summary details on all their neighbors. In the experiments reported here, SPIKE predicted service spikes 30 minutes into future with recalls and precision of 75% and above. Also, SPIKE performed relatively better than other widely-used learning methods (neural nets, random forests, logistic regression). |
| Spike Timing Dependent Plasticity (STDP) |
In this work, we propose ReStoCNet, a residual stochastic multilayer convolutional Spiking Neural Network (SNN) composed of binary kernels, to reduce the synaptic memory footprint and enhance the computational efficiency of SNNs for complex pattern recognition tasks. ReStoCNet consists of an input layer followed by stacked convolutional layers for hierarchical input feature extraction, pooling layers for dimensionality reduction, and fully-connected layer for inference. In addition, we introduce residual connections between the stacked convolutional layers to improve the hierarchical feature learning capability of deep SNNs. We propose Spike Timing Dependent Plasticity (STDP) based probabilistic learning algorithm, referred to as Hybrid-STDP (HB-STDP), incorporating Hebbian and anti-Hebbian learning mechanisms, to train the binary kernels forming ReStoCNet in a layer-wise unsupervised manner. We demonstrate the efficacy of ReStoCNet and the presented HB-STDP based unsupervised training methodology on the MNIST and CIFAR-10 datasets. We show that residual connections enable the deeper convolutional layers to self-learn useful high-level input features and mitigate the accuracy loss observed in deep SNNs devoid of residual connections. The proposed ReStoCNet offers >20x kernel memory compression compared to full-precision (32-bit) SNN while yielding high enough classification accuracy on the chosen pattern recognition tasks. |
| Spike-and-Slab LASSO | SSLASSO |
| SpikeProp | For a network of spiking neurons that encodes information in the timing of individual spike times, we derive a supervised learning rule, SpikeProp, akin to traditional error-backpropagation. With this algorithm, we demonstrate how networks of spiking neurons with biologically reasonable action potentials can perform complex non-linear classification in fast temporal coding just as well as rate-coded networks. We perform experiments for the classical XOR problem, when posed in a temporal setting, as well as for a number of other benchmark datasets. Comparing the (implicit) number of spiking neurons required for the encoding of the interpolated XOR problem, the trained networks demonstrate that temporal coding is a viable code for fast neural information processing, and as such requires less neurons than instantaneous rate-coding. Furthermore, we find that reliable temporal computation in the spiking networks was only accomplished when using spike response functions with a time constant longer than the coding interval, as has been predicted by theoretical considerations. |
| Spike-Triggered non-Negative Matrix Factorization (STNMF) |
Neurons in sensory systems often pool inputs over arrays of presynaptic cells, giving rise to functional subunits inside a neuron´s receptive field. The organization of these subunits provides a signature of the neuron´s presynaptic functional connectivity and determines how the neuron integrates sensory stimuli. Here we introduce the method of spike-triggered non-negative matrix factorization for detecting the layout of subunits within a neuron´s receptive field. The method only requires the neuron´s spiking responses under finely structured sensory stimulation and is therefore applicable to large populations of simultaneously recorded neurons. Applied to recordings from ganglion cells in the salamander retina, the method retrieves the receptive fields of presynaptic bipolar cells, as verified by simultaneous bipolar and ganglion cell recordings. The identified subunit layouts allow improved predictions of ganglion cell responses to natural stimuli and reveal shared bipolar cell input into distinct types of ganglion cells. Characterizing Neuronal Circuits with Spike-triggered Non-negative Matrix Factorization |
| Spiking Neural Network (SNN) |
Spiking Neural Networks (SNNs) are distributed systems whose computing elements, or neurons, are characterized by analog internal dynamics and by digital and sparse inter-neuron, or synaptic, communications. The sparsity of the synaptic spiking inputs and the corresponding event-driven nature of neural processing can be leveraged by hardware implementations to obtain significant energy reductions as compared to conventional Artificial Neural Networks (ANNs). SNNs can be used not only as coprocessors to carry out given computing tasks, such as classification, but also as learning machines that adapt their internal parameters, e.g., their synaptic weights, on the basis of data and of a learning criterion. This paper provides an overview of models, learning rules, and applications of SNNs from the viewpoint of stochastic signal processing. |
| Spinnaker | Spinnaker is an open source, multi-cloud continuous delivery platform for releasing software changes with high velocity and confidence. |
| Spirtes Glymour Scheines Algorithm (SGS) |
A.) Form the complete undirected graph H on the vertex set V. B.) For each pair of vertices A and B, if there exists a subset S of V such that A and B are d-separated given S, remove the edge between A and B from H. C.) Let K be the undirected graph resulting from step B). For each triple of vertices A B, and C such that the pair A and B and the pair B and C are each adjacent in K (written as A – B – C) but the pair A and C are not adjacent in K, orient A – B – C as A -> B <- C if and only if there is no subset S of {B} È V that d-separates A and C. D.) repeat · If A -> B, B and C are adjacent, A and C are not adjacent, and there is no arrowhead at B, then orient B – C as B -> C. · If there is a directed path from A to B, and an edge between A and B, then orient A – B as A -> B. until no more edges can be oriented. |
| Spline-Based Probability Calibration (SplineCalib) |
In many classification problems it is desirable to output well-calibrated probabilities on the different classes. We propose a robust, non-parametric method of calibrating probabilities called SplineCalib that utilizes smoothing splines to determine a calibration function. We demonstrate how applying certain transformations as part of the calibration process can improve performance on problems in deep learning and other domains where the scores tend to be ‘overconfident’. We adapt the approach to multi-class problems and find that better calibration can improve accuracy as well as log-loss by better resolving uncertain cases. Finally, we present a cross-validated approach to calibration which conserves data. Significant improvements to log-loss and accuracy are shown on several different problems. We also introduce the ml-insights python package which contains an implementation of the SplineCalib algorithm. |
| SplineNet | We present SplineNets, a practical and novel approach for using conditioning in convolutional neural networks (CNNs). SplineNets are continuous generalizations of neural decision graphs, and they can dramatically reduce runtime complexity and computation costs of CNNs, while maintaining or even increasing accuracy. Functions of SplineNets are both dynamic (i.e., conditioned on the input) and hierarchical (i.e., conditioned on the computational path). SplineNets employ a unified loss function with a desired level of smoothness over both the network and decision parameters, while allowing for sparse activation of a subset of nodes for individual samples. In particular, we embed infinitely many function weights (e.g. filters) on smooth, low dimensional manifolds parameterized by compact B-splines, which are indexed by a position parameter. Instead of sampling from a categorical distribution to pick a branch, samples choose a continuous position to pick a function weight. We further show that by maximizing the mutual information between spline positions and class labels, the network can be optimally utilized and specialized for classification tasks. Experiments show that our approach can significantly increase the accuracy of ResNets with negligible cost in speed, matching the precision of a 110 level ResNet with a 32 level SplineNet. |
| SPLINE-Net | This paper solves the Sparse Photometric stereo through Lighting Interpolation and Normal Estimation using a generative Network (SPLINE-Net). SPLINE-Net contains a lighting interpolation network to generate dense lighting observations given a sparse set of lights as inputs followed by a normal estimation network to estimate surface normals. Both networks are jointly constrained by the proposed symmetric and asymmetric loss functions to enforce isotropic constrain and perform outlier rejection of global illumination effects. SPLINE-Net is verified to outperform existing methods for photometric stereo of general BRDFs by using only ten images of different lights instead of using nearly one hundred images. |
| Split Batch Normalization (Split-BN) |
Recent work has shown that using unlabeled data in semi-supervised learning is not always beneficial and can even hurt generalization, especially when there is a class mismatch between the unlabeled and labeled examples. We investigate this phenomenon for image classification on the CIFAR-10 and the ImageNet datasets, and with many other forms of domain shifts applied (e.g. salt-and-pepper noise). Our main contribution is Split Batch Normalization (Split-BN), a technique to improve SSL when the additional unlabeled data comes from a shifted distribution. We achieve it by using separate batch normalization statistics for unlabeled examples. Due to its simplicity, we recommend it as a standard practice. Finally, we analyse how domain shift affects the SSL training process. In particular, we find that during training the statistics of hidden activations in late layers become markedly different between the unlabeled and the labeled examples. |
| Splitability Annotations (SA) |
Data movement is a major bottleneck in parallel data-intensive applications. In response to this problem, researchers have proposed new runtimes and intermediate representations (IRs) that apply optimizations such as loop fusion under existing library APIs. Even though these runtimes generally do no require changes to user code, they require intrusive changes to the library itself: often, all the library functions need to be rewritten for a new IR or virtual machine. In this paper, we propose a new abstraction called splitability annotations (SAs) that enables key data movement optimizations on black-box library functions. SAs only require that users add an annotation for existing, unmodified functions and implement a small API to split data values in the library. Together, this interface describes how to partition values that are passed among functions to enable data pipelining and automatic parallelization while respecting each library’s correctness constraints. We implement SAs in a system called Mozart. Without modifying any library function, on workloads using NumPy and Pandas in Python and Intel MKL in C, Mozart provides performance competitive with intrusive solutions that require rewriting libraries in many cases, can sometimes improve performance over past systems by up to 2x, and accelerates workloads by up to 30x. |
| Split-Apply-Combine Strategy | In a split-apply-combine strategy you break up a big problem into manageable pieces, operate on each piece independently and then put all the pieces back together. |
| Splitted Isotonic Regression (ISO-SPLIT) |
A limitation of many clustering algorithms is the requirement to tune adjustable parameters for each application or even for each dataset. Some algorithms require an \emph{a priori} estimate of the number of clusters while density-based techniques usually require a scale parameter. Other parametric methods, such as mixture modeling, make assumptions about the underlying cluster distributions. Here we introduce a non-parametric clustering method that does not involve tunable parameters and only assumes that clusters are unimodal, in the sense that they have a single point of maximal density when projected onto any line, and that clusters are separated from one another by a separating hyperplane of relatively lower density. The technique uses a non-parametric algorithm—isotonic regression—as the kernel operation repeated at every iteration. We carry out a rigorous hypothesis test for whether pairs of clusters should be merged based upon Monte Carlo sampling of a statistic. We compare the method against k-means++, DBSCAN, and Gaussian mixture algorithms and show in simulations that it performs better than these standard methods in many situations. The algorithm’s utility is also demonstrated in the context of ‘spike sorting’ of neural electrical recordings. The source code for the algorithm is freely available. |
| SPLOM Chart | The scatterplot matrix, known acronymically as SPLOM, is a relatively uncommon graphical tool that uses multiple scatterplots to determine the correlation (if any) between a series of variables. These scatterplots are then organized into a matrix, making it easy to look at all the potential correlations in one place. SPLOMs, invented by John Hartigan in 1975, allow data aficionados to quickly realize any interesting correlations between parameters in the data set. |
| SPM-Tracker | The greatest challenge facing visual object tracking is the simultaneous requirements on robustness and discrimination power. In this paper, we propose a SiamFC-based tracker, named SPM-Tracker, to tackle this challenge. The basic idea is to address the two requirements in two separate matching stages. Robustness is strengthened in the coarse matching (CM) stage through generalized training while discrimination power is enhanced in the fine matching (FM) stage through a distance learning network. The two stages are connected in series as the input proposals of the FM stage are generated by the CM stage. They are also connected in parallel as the matching scores and box location refinements are fused to generate the final results. This innovative series-parallel structure takes advantage of both stages and results in superior performance. The proposed SPM-Tracker, running at 120fps on GPU, achieves an AUC of 0.687 on OTB-100 and an EAO of 0.434 on VOT-16, exceeding other real-time trackers by a notable margin. |
| Spoken Dialogue System (SDS) |
A spoken dialog system is a computer system able to converse with a human with voice. It has two essential components that do not exist in a text dialog system: a speech recognizer and a text-to-speech module. In can be further distinguished from command and control speech systems that can respond to requests but do not attempt to maintain continuity over time. |
| Spoken Language Understanding (SLU) |
Robust Spoken Language Understanding via Paraphrasing |
| Spontaneous Clustering | We propose a new method for clustering based on the local minimization of the \gamma-divergence, which we call the spontaneous clustering. The greatest advantage of the proposed method is that it automatically detects the number of clusters that adequately reflect the data structure. In contrast, exiting methods such as K-means, fuzzy c-means, and model based clustering need to prescribe the number of clusters. We detect all the local minimum points of the \gamma-divergence, which are defined as the centers of clusters. A necessary and sufficient condition for the \gamma-divergence to have the local minimum points is also derived in a simple setting. A simulation study and a real data analysis are performed to compare our proposal with existing methods. |
| Spotlight Analysis | New name for an old way of interpreting an interaction between a continuous and a categorical grouping variable in a regression model. The basic idea of spotlight analysis is to compare the mean satisfaction score of the two groups at specific values of the continuous covariate. |
| Spotting anomalies with Privileged Information (SPI) |
We introduce a new unsupervised anomaly detection ensemble called SPI which can harness privileged information – data available only for training examples but not for (future) test examples. Our ideas build on the Learning Using Privileged Information (LUPI) paradigm pioneered by Vapnik et al. [19,17], which we extend to unsupervised learning and in particular to anomaly detection. SPI (for Spotting anomalies with Privileged Information) constructs a number of frames/fragments of knowledge (i.e., density estimates) in the privileged space and transfers them to the anomaly scoring space through ‘imitation’ functions that use only the partial information available for test examples. Our generalization of the LUPI paradigm to unsupervised anomaly detection shepherds the field in several key directions, including (i) domain knowledge-augmented detection using expert annotations as PI, (ii) fast detection using computationally-demanding data as PI, and (iii) early detection using ‘historical future’ data as PI. Through extensive experiments on simulated and real datasets, we show that augmenting privileged information to anomaly detection significantly improves detection performance. We also demonstrate the promise of SPI under all three settings (i-iii); with PI capturing expert knowledge, computationally expensive features, and future data on three real world detection tasks. |
| SpotTune | Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained on the source task using data from the target task. In this paper, we propose an adaptive fine-tuning approach, called SpotTune, which finds the optimal fine-tuning strategy per instance for the target data. In SpotTune, given an image from the target task, a policy network is used to make routing decisions on whether to pass the image through the fine-tuned layers or the pre-trained layers. We conduct extensive experiments to demonstrate the effectiveness of the proposed approach. Our method outperforms the traditional fine-tuning approach on 12 out of 14 standard datasets.We also compare SpotTune with other state-of-the-art fine-tuning strategies, showing superior performance. On the Visual Decathlon datasets, our method achieves the highest score across the board without bells and whistles. |
| spray | spray is an open-source toolkit for building REST/HTTP-based integration layers on top of Scala and Akka. Being asynchronous, actor-based, fast, lightweight, modular and testable it’s a great way to connect your Scala applications to the world. |
| Spreading Activation | Spreading activation is a method for searching associative networks, neural networks, or semantic networks. The search process is initiated by labeling a set of source nodes (e.g. concepts in a semantic network) with weights or “activation” and then iteratively propagating or “spreading” that activation out to other nodes linked to the source nodes. Most often these “weights” are real values that decay as activation propagates through the network. When the weights are discrete this process is often referred to as marker passing. Activation may originate from alternate paths, identified by distinct markers, and terminate when two alternate paths reach the same node. |
| Spreadmart | A spreadmart (spreadsheet data mart) is a situation in which a company’s employees has inconsistent views of corporate data because each department relies on the data from their own spreadsheets. |
| Spring for Apache Hadoop | Spring for Apache Hadoop simplifies developing Apache Hadoop by providing a unified configuration model and easy to use APIs for using HDFS, MapReduce, Pig, and Hive. It also provides integration with other Spring ecosystem project such as Spring Integration and Spring Batch enabling you to develop solutions for big data ingest/export and Hadoop workflow orchestration. |
| SPSA-FSR | This manuscript presents the following: (1) an improved version of the Binary Simultaneous Perturbation Stochastic Approximation (SPSA) Method for feature selection in machine learning (Aksakalli and Malekipirbazari, Pattern Recognition Letters, Vol. 75, 2016) based on non-monotone iteration gains computed via the Barzilai and Borwein (BB) method, (2) its adaptation for feature ranking, and (3) comparison against popular methods on public benchmark datasets. The improved method, which we call SPSA-FSR, dramatically reduces the number of iterations required for convergence without impacting solution quality. SPSA-FSR can be used for feature ranking and feature selection both for classification and regression problems. After a review of the current state-of-the-art, we discuss our improvements in detail and present three sets of computational experiments: (1) comparison of SPSA-FS as a (wrapper) feature selection method against sequential methods as well as genetic algorithms, (2) comparison of SPSA-FS as a feature ranking method in a classification setting against random forest importance, chi-squared, and information main methods, and (3) comparison of SPSA-FS as a feature ranking method in a regression setting against minimum redundancy maximum relevance (MRMR), RELIEF, and linear correlation methods. The number of features in the datasets we use range from a few dozens to a few thousands. Our results indicate that SPSA-FS converges to a good feature set in no more than 100 iterations and therefore it is quite fast for a wrapper method. SPSA-FS also outperforms popular feature selection as well as feature ranking methods in majority of test cases, sometimes by a large margin, and it stands as a promising new feature selection and ranking method. |
| SpykeTorch | Application of deep convolutional spiking neural networks (SNNs) to artificial intelligence (AI) tasks has recently gained a lot of interest since SNNs are hardware-friendly and energy-efficient. Unlike the non-spiking counterparts, most of the existing SNN simulation frameworks are not practically efficient enough for large-scale AI tasks. In this paper, we introduce SpykeTorch, an open-source high-speed simulation framework based on PyTorch. This framework simulates convolutional SNNs with at most one spike per neuron and the rank-order encoding scheme. In terms of learning rules, both spike-timing-dependent plasticity (STDP) and reward-modulated STDP (R-STDP) are implemented, but other rules could be implemented easily. Apart from the aforementioned properties, SpykeTorch is highly generic and capable of reproducing the results of various studies. Computations in the proposed framework are tensor-based and totally done by PyTorch functions, which in turn brings the ability of just-in-time optimization for running on CPUs, GPUs, or Multi-GPU platforms. |
| Spyre | Spyre is a Web Application Framework for providing a simple user interface for Python data projects. Spyre runs on the minimalist python web framework, cherrypy, with jinja2 templating. At it’s heart, spyre is about data and data visualization, so you’ll also need pandas and matplotlib. |
| SQLite | SQLite is a software library that implements a self-contained, serverless, zero-configuration, transactional SQL database engine. SQLite is a relational database management system contained in a C programming library. In contrast to other database management systems, SQLite is not a separate process that is accessed from the client application, but an integral part of it. SQLite is ACID-compliant and implements most of the SQL standard, using a dynamically and weakly typed SQL syntax that does not guarantee the domain integrity. SQLite is a popular choice as embedded database for local/client storage in application software such as web browsers. It is arguably the most widely deployed database engine, as it is used today by several widespread browsers, operating systems, and embedded systems, among others. SQLite has bindings to many programming languages. The source code for SQLite is in the public domain. RSQLite |
| SQLScript | The motivation for SQLScript is to embed data-intensive application logic into the database. As of today, applications only offload very limited functionality into the database using SQL, most of the application logic is normally executed in an application server. This has the effect that data to be operated upon needs to be copied from the database into the application server and vice versa. When executing data intensive logic, this copying of data is very expensive in terms of processor and data transfer time. Moreover, when using an imperative language like ABAP or JAVA for processing data, developers tend to write algorithms which follow a one tuple at a time semantics (for example looping over rows in a table). However, these algorithms are hard to optimize and parallelize compared to declarative set-oriented languages such as SQL. The SAP HANA database is optimized for modern technology trends and takes advantage of modern hardware, for example, by having data residing in main-memory and allowing massive-parallelization on multi-core CPUs. The goal of the SAP HANA database is to optimally support application requirements by leveraging such hardware. To this end, the SAP HANA database exposes a very sophisticated interface to the application consisting of many languages. The expressiveness of these languages far exceeds that attainable with OpenSQL. The set of SQL extensions for the SAP HANA database that allow developers to push data intensive logic into the database is called SQLScript. Conceptually SQLScript is related to stored procedures as defined in the SQL standard, but SQLScript is designed to provide superior optimization possibilities. SQLScript should be used in cases where other modeling constructs of SAP HANA, for example analytic views or attribute views are not sufficient. For more information on how to best exploit the different view types, see ‘Exploit Underlying Engine’. The set of SQL extensions are the key to avoiding massive data copies to the application server and for leveraging sophisticated parallel execution strategies of the database. SQLScript addresses the following problems: ● Decomposing an SQL query can only be done using views. However when decomposing complex queries using views, all intermediate results are visible and must be explicitly typed. Moreover SQL views cannot be parameterized which limits their reuse. In particular they can only be used like tables and embedded into other SQL statements. ● SQL queries do not have features to express business logic (for example a complex currency conversion). As a consequence such a business logic cannot be pushed down into the database (even if it is mainly based on standard aggregations like SUM(Sales), etc.). ● An SQL query can only return one result at a time. As a consequence the computation of related result sets must be split into separate, usually unrelated, queries. ● As SQLScript encourages developers to implement algorithms using a set-oriented paradigm and not using a one tuple at a time paradigm, imperative logic is required, for example by iterative approximation algorithms. Thus it is possible to mix imperative constructs known from stored procedures with declarative ones. |
| SQuantizer | Deep neural networks have achieved state-of-the-art accuracies in a wide range of computer vision, speech recognition, and machine translation tasks. However the limits of memory bandwidth and computational power constrain the range of devices capable of deploying these modern networks. To address this problem, we propose SQuantizer, a new training method that jointly optimizes for both sparse and low-precision neural networks while maintaining high accuracy and providing a high compression rate. This approach brings sparsification and low-bit quantization into a single training pass, employing these techniques in an order demonstrated to be optimal. Our method achieves state-of-the-art accuracies using 4-bit and 2-bit precision for ResNet18, MobileNet-v2 and ResNet50, even with high degree of sparsity. The compression rates of 18x for ResNet18 and 17x for ResNet50, and 9x for MobileNet-v2 are obtained when SQuantizing both weights and activations within 1% and 2% loss in accuracy for ResNets and MobileNet-v2 respectively. An extension of these techniques to object detection also demonstrates high accuracy on YOLO-v2. Additionally, our method allows for fast single pass training, which is important for rapid prototyping and neural architecture search techniques. Finally extensive results from this simultaneous training approach allows us to draw some useful insights into the relative merits of sparsity and quantization. |
| Squared-Loss Mutual Information (SMI) |
➘ “Squared-Loss Mutual Information Regularization” |
| Squared-Loss Mutual Information Regularization (SMIR) |
We propose squared-loss mutual information regularization (SMIR) for multi-class probabilistic classi cation, following the information maximization principle. SMIR is convex under mild conditions and thus improves the nonconvexity of mutual information regularization. It offers all of the following four abilities to semi-supervised algorithms: Analytical solution, out-of-sample/multi-class classification, and probabilistic output. Furthermore, novel generalization error bounds are derived. Experiments show SMIR compares favorably with state-of-the-art methods. |
| Squeezed Very Deep Convolutional Neural Network (SVDCNN) |
Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the trained network to platforms with memory and processing constraints. We propose to modify the structure of the Very Deep Convolutional Neural Networks (VDCNN) model to fit mobile platforms constraints and keep performance. In this paper, we evaluate the impact of Temporal Depthwise Separable Convolutions and Global Average Pooling in the network parameters, storage size, and latency. The squeezed model (SVDCNN) is between 10x and 20x smaller, depending on the network depth, maintaining a maximum size of 6MB. Regarding accuracy, the network experiences a loss between 0.4% and 1.3% and obtains lower latencies compared to the baseline model. |
| SqueezeNet | SqueezeNet is the name of a deep neural network that was released in 2016. SqueezeNet was developed by researchers at DeepScale, University of California, Berkeley, and Stanford University. In designing SqueezeNet, the authors’ goal was to create a smaller neural network with fewer parameters that can more easily fit into computer memory and can more easily be transmitted over a computer network. Review: SqueezeNet (Image Classification) |
| Squeeze-SegNet | The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant advances. However, if they were limited to classification tasks, nowadays with contributions from Scientific Communities who are embarking in this field, they have become very useful in higher level tasks such as object detection and pixel-wise semantic segmentation. Thus, brilliant ideas in the field of semantic segmentation with deep learning have completed the state of the art of accuracy, however this architectures become very difficult to apply in embedded systems as is the case for autonomous driving. We present a new Deep fully Convolutional Neural Network for pixel-wise semantic segmentation which we call Squeeze-SegNet. The architecture is based on Encoder-Decoder style. We use a SqueezeNet-like encoder and a decoder formed by our proposed squeeze-decoder module and upsample layer using downsample indices like in SegNet and we add a deconvolution layer to provide final multi-channel feature map. On datasets like Camvid or City-states, our net gets SegNet-level accuracy with less than 10 times fewer parameters than SegNet. |
| SSIMLayer | Deeper convolutional neural networks provide more capacity to approximate complex mapping functions. However, increasing network depth imposes difficulties on training and increases model complexity. This paper presents a new nonlinear computational layer of considerably high capacity to the deep convolutional neural network architectures. This layer performs a set of comprehensive convolution operations that mimics the overall function of the human visual system (HVS) via focusing on learning structural information in its input. The core of its computations is evaluating the components of the structural similarity metric (SSIM) in a setting that allows the kernels to learn to match structural information. The proposed SSIMLayer is inherently nonlinear and hence, it does not require subsequent nonlinear transformations. Experiments conducted on CIFAR-10 benchmark demonstrates that the SSIMLayer provides better convergence than the traditional convolutional layer, bypasses the need for nonlinear transformations and shows more robustness against noise perturbations and adversarial attacks. |
| Stability | A learning system is said to be stable if no pattern in the training data changes its category after a finite number of learning iterations. |
| Stable Marriage Problem (SMP) |
In mathematics, economics, and computer science, the stable marriage problem (also stable matching problem or SMP) is the problem of finding a stable matching between two equally sized sets of elements given an ordering of preferences for each element. A matching is a mapping from the elements of one set to the elements of the other set. A matching is stable whenever it is not the case that both: 1. some given element A of the first matched set prefers some given element B of the second matched set over the element to which A is already matched, and 2. B also prefers A over the element to which B is already matched In other words, a matching is stable when there does not exist any match (A, B) by which both A and B are individually better off than they would be with the element to which they are currently matched. The stable marriage problem is commonly stated in terms of heterosexual marriages and binary genders: ‘Given n men and n women, where each person has ranked all members of the opposite sex in order of preference, marry the men and women together such that there are no two people of opposite sex who would both rather have each other than their current partners. When there are no such pairs of people, the set of marriages is deemed stable.’ Algorithms for finding solutions to the stable marriage problem have applications in a variety of real-world situations, perhaps the best known of these being in the assignment of graduating medical students to their first hospital appointments. In 2012, the Nobel Prize in Economics was awarded to Lloyd S. Shapley and Alvin E. Roth ‘for the theory of stable allocations and the practice of market design.’ ➚ “Gale-Shapley Algorithm” |
| StableOpt | In this paper, we consider the problem of Gaussian process (GP) optimization with an added robustness requirement: The returned point may be perturbed by an adversary, and we require the function value to remain as high as possible even after this perturbation. This problem is motivated by settings in which the underlying functions during optimization and implementation stages are different, or when one is interested in finding an entire region of good inputs rather than only a single point. We show that standard GP optimization algorithms do not exhibit the desired robustness properties, and provide a novel confidence-bound based algorithm StableOpt for this purpose. We rigorously establish the required number of samples for StableOpt to find a near-optimal point, and we complement this guarantee with an algorithm-independent lower bound. We experimentally demonstrate several potential applications of interest using real-world data sets, and we show that StableOpt consistently succeeds in finding a stable maximizer where several baseline methods fail. |
| Stack Long Short-Term Memory | Parallelizable Stack Long Short-Term Memory |
| Stacked Area Plot | Stacked Area Graphs work in the same way as simple Area Graphs do, except for the use of multiple data series that start each point from the point left by the previous data series. The entire graph represents the total of all the data plotted. Stacked Area Graphs also use area to convey whole numbers, so they do not work for negative values. Overall, they are useful for comparing multiple variables changing over an interval. areaplot |
| Stacked Autoencoders | A stacked autoencoder is a neural network consisting of multiple layers of sparse autoencoders in which the outputs of each layer is wired to the inputs of the successive layer. The greedy layerwise approach for pretraining a deep network works by training each layer in turn. In this page, you will find out how autoencoders can be “stacked” in a greedy layerwise fashion for pretraining (initializing) the weights of a deep network. |
| Stacked Bidirectional LSTM/GRU Network | Videos have become ubiquitous on the Internet. And video analysis can provide lots of information for detecting and recognizing objects as well as help people understand human actions and interactions with the real world. However, facing data as huge as TB level, effective methods should be applied. Recurrent neural network (RNN) architecture has wildly been used on many sequential learning problems such as Language Model, Time-Series Analysis, etc. In this paper, we propose some variations of RNN such as stacked bidirectional LSTM/GRU network with attention mechanism to categorize large-scale video data. We also explore different multimodal fusion methods. Our model combines both visual and audio information on both video and frame level and received great result. Ensemble methods are also applied. Because of its multimodal characteristics, we decide to call this method Deep Multimodal Learning(DML). Our DML-based model was trained on Google Cloud and our own server and was tested in a well-known video classification competition on Kaggle held by Google. |
| Stacked Deconvolutional Network (SDN) |
Recent progress in semantic segmentation has been driven by improving the spatial resolution under Fully Convolutional Networks (FCNs). To address this problem, we propose a Stacked Deconvolutional Network (SDN) for semantic segmentation. In SDN, multiple shallow deconvolutional networks, which are called as SDN units, are stacked one by one to integrate contextual information and guarantee the fine recovery of localization information. Meanwhile, inter-unit and intra-unit connections are designed to assist network training and enhance feature fusion since the connections improve the flow of information and gradient propagation throughout the network. Besides, hierarchical supervision is applied during the upsampling process of each SDN unit, which guarantees the discrimination of feature representations and benefits the network optimization. We carry out comprehensive experiments and achieve the new state-of-the-art results on three datasets, including PASCAL VOC 2012, CamVid, GATECH. In particular, our best model without CRF post-processing achieves an intersection-over-union score of 86.6% in the test set. |
| Stacked Denoising Autoencoder (SdA) |
A stacked denoising autoencoder is to a denoising autoencoder what a deep-belief network is to a restricted Boltzmann machine. A key function of SDAs, and deep learning more generally, is unsupervised pre-training, layer by layer, as input is fed through. Once each layer is pre-trained to conduct feature selection and extraction on the input from the preceding layer, a second stage of supervised fine-tuning can follow. A word on stochastic corruption in SDAs: Denoising autoencoders shuffle data around and learn about that data by attempting to reconstruct it. The act of shuffling is the noise, and the job of the network is to recognize the features within the noise that will allow it to classify the input. When a network is being trained, it generates a model, and measures the distance between that model and the benchmark through a loss function. Its attempts to minimize the loss function involve resampling the shuffled inputs and re-reconstructing the data, until it finds those inputs which bring its model closest to what it has been told is true. The serial resamplings are based on a generative model to randomly provide data to be processed. This is known as a Markov Chain, and more specifically, a Markov Chain Monte Carlo algorithm that steps through the data set seeking a representative sampling of indicators that can be used to construct more and more complex features. |
| Stacked Dilated Convolution (SDC) |
Dense pixel matching is important for many computer vision tasks such as disparity and flow estimation. We present a robust, unified descriptor network that considers a large context region with high spatial variance. Our network has a very large receptive field and avoids striding layers to maintain spatial resolution. These properties are achieved by creating a novel neural network layer that consists of multiple, parallel, stacked dilated convolutions (SDC). Several of these layers are combined to form our SDC descriptor network. In our experiments, we show that our SDC features outperform state-of-the-art feature descriptors in terms of accuracy and robustness. In addition, we demonstrate the superior performance of SDC in state-of-the-art stereo matching, optical flow and scene flow algorithms on several famous public benchmarks. |
| Stacked Generalization (Blending) |
Stacking (sometimes called stacked generalization) involves training a learning algorithm to combine the predictions of several other learning algorithms. First, all of the other algorithms are trained using the available data, then a combiner algorithm is trained to make a final prediction using all the predictions of the other algorithms as additional inputs. If an arbitrary combiner algorithm is used, then stacking can theoretically represent any of the ensemble techniques described in this article, although in practice, a single-layer logistic regression model is often used as the combiner. Stacking typically yields performance better than any single one of the trained models. It has been successfully used on both supervised learning tasks (regression) and unsupervised learning (density estimation). It has also been used to estimate bagging’s error rate. It has been reported to out-perform Bayesian model-averaging. The two top-performers in the Netflix competition utilized blending, which may be considered to be a form of stacking. |
| Stacked Generative Adversarial Networks (SGAN) |
In this paper we aim to leverage the powerful bottom-up discriminative representations to guide a top-down generative model. We propose a novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a discriminative bottom-up deep network. Our model consists of a top-down stack of GANs, each trained to generate ‘plausible’ lower-level representations, conditioned on higher-level representations. A representation discriminator is introduced at each feature hierarchy to encourage the representation manifold of the generator to align with that of the bottom-up discriminative network, providing intermediate supervision. In addition, we introduce a conditional loss that encourages the use of conditional information from the layer above, and a novel entropy loss that maximizes a variational lower bound on the conditional entropy of generator outputs. To the best of our knowledge, the entropy loss is the first attempt to tackle the conditional model collapse problem that is common in conditional GANs. We first train each GAN of the stack independently, and then we train the stack end-to-end. Unlike the original GAN that uses a single noise vector to represent all the variations, our SGAN decomposes variations into multiple levels and gradually resolves uncertainties in the top-down generative process. Experiments demonstrate that SGAN is able to generate diverse and high-quality images, as well as being more interpretable than a vanilla GAN. |
| Stacked Kernel Network (SKN) |
Kernel methods are powerful tools to capture nonlinear patterns behind data. They implicitly learn high (even infinite) dimensional nonlinear features in the Reproducing Kernel Hilbert Space (RKHS) while making the computation tractable by leveraging the kernel trick. Classic kernel methods learn a single layer of nonlinear features, whose representational power may be limited. Motivated by recent success of deep neural networks (DNNs) that learn multi-layer hierarchical representations, we propose a Stacked Kernel Network (SKN) that learns a hierarchy of RKHS-based nonlinear features. SKN interleaves several layers of nonlinear transformations (from a linear space to a RKHS) and linear transformations (from a RKHS to a linear space). Similar to DNNs, a SKN is composed of multiple layers of hidden units, but each parameterized by a RKHS function rather than a finite-dimensional vector. We propose three ways to represent the RKHS functions in SKN: (1)nonparametric representation, (2)parametric representation and (3)random Fourier feature representation. Furthermore, we expand SKN into CNN architecture called Stacked Kernel Convolutional Network (SKCN). SKCN learning a hierarchy of RKHS-based nonlinear features by convolutional operation with each filter also parameterized by a RKHS function rather than a finite-dimensional matrix in CNN, which is suitable for image inputs. Experiments on various datasets demonstrate the effectiveness of SKN and SKCN, which outperform the competitive methods. |
| Stackelberg GAN | We study the problem of alleviating the instability issue in the GAN training procedure via new architecture design. The discrepancy between the minimax and maximin objective values could serve as a proxy for the difficulties that the alternating gradient descent encounters in the optimization of GANs. In this work, we give new results on the benefits of multi-generator architecture of GANs. We show that the minimax gap shrinks to $\epsilon$ as the number of generators increases with rate $\widetilde{O}(1/\epsilon)$. This improves over the best-known result of $\widetilde{O}(1/\epsilon^2)$. At the core of our techniques is a novel application of Shapley-Folkman lemma to the generic minimax problem, where in the literature the technique was only known to work when the objective function is restricted to the Lagrangian function of a constraint optimization problem. Our proposed Stackelberg GAN performs well experimentally in both synthetic and real-world datasets, improving Fr\’echet Inception Distance by $14.61\%$ over the previous multi-generator GANs on the benchmark datasets. |
| StackExchange | Existing keyphrase generation studies suffer from the problems of generating duplicate phrases and deficient evaluation based on a fixed number of predicted phrases. We propose a recurrent generative model that generates multiple keyphrases sequentially from a text, with specific modules that promote generation diversity. We further propose two new metrics that consider a variable number of phrases. With both existing and proposed evaluation setups, our model demonstrates superior performance to baselines on three types of keyphrase generation datasets, including two newly introduced in this work: StackExchange and TextWorld ACG. In contrast to previous keyphrase generation approaches, our model generates sets of diverse keyphrases of a variable number. |
| Stacking-Based Deep Neural Network (S-DNN) |
Stacking-based deep neural network (S-DNN) is aggregated with pluralities of basic learning modules, one after another, to synthesize a deep neural network (DNN) alternative for pattern classification. Contrary to the DNNs trained end to end by backpropagation (BP), each S-DNN layer, i.e., a self-learnable module, is to be trained decisively and independently without BP intervention. In this paper, a ridge regression-based S-DNN, dubbed deep analytic network (DAN), along with its kernelization (K-DAN), are devised for multilayer feature re-learning from the pre-extracted baseline features and the structured features. Our theoretical formulation demonstrates that DAN/K-DAN re-learn by perturbing the intra/inter-class variations, apart from diminishing the prediction errors. We scrutinize the DAN/K-DAN performance for pattern classification on datasets of varying domains – faces, handwritten digits, generic objects, to name a few. Unlike the typical BP-optimized DNNs to be trained from gigantic datasets by GPU, we disclose that DAN/K-DAN are trainable using only CPU even for small-scale training sets. Our experimental results disclose that DAN/K-DAN outperform the present S-DNNs and also the BP-trained DNNs, including multiplayer perceptron, deep belief network, etc., without data augmentation applied. |
| Staircase Network | Language recognition system is typically trained directly to optimize classification error on the target language labels, without using the external, or meta-information in the estimation of the model parameters. However labels are not independent of each other, there is a dependency enforced by, for example, the language family, which affects negatively on classification. The other external information sources (e.g. audio encoding, telephony or video speech) can also decrease classification accuracy. In this paper, we attempt to solve these issues by constructing a deep hierarchical neural network, where different levels of meta-information are encapsulated by attentive prediction units and also embedded into the training progress. The proposed method learns auxiliary tasks to obtain robust internal representation and to construct a variant of attentive units within the hierarchical model. The final result is the structural prediction of the target language and a closely related language family. The algorithm reflects a ‘staircase’ way of learning in both its architecture and training, advancing from the fundamental audio encoding to the language family level and finally to the target language level. This process not only improves generalization but also tackles the issues of imbalanced class priors and channel variability in the deep neural network model. Our experimental findings show that the proposed architecture outperforms the state-of-the-art i-vector approaches on both small and big language corpora by a significant margin. |
| Stale History | We present a sample path dependent measure of causal influence between time series. The proposed causal measure is a random sequence, a realization of which enables identification of specific patterns that give rise to high levels of causal influence. We show that these patterns cannot be identified by existing measures such as directed information (DI). We demonstrate how sequential prediction theory may be leveraged to estimate the proposed causal measure and introduce a notion of regret for assessing the performance of such estimators. We prove a finite sample bound on this regret that is determined by the worst case regret of the sequential predictors used in the estimator. Justification for the proposed measure is provided through a series of examples, simulations, and application to stock market data. Within the context of estimating DI, we show that, because joint Markovicity of a pair of processes does not imply the marginal Markovicity of individual processes, commonly used plug-in estimators of DI will be biased for a large subset of jointly Markov processes. We introduce a notion of DI with ‘stale history’, which can be combined with a plug-in estimator to upper and lower bound the DI when marginal Markovicity does not hold. |
| Staleness | Most distributed machine learning (ML) systems store a copy of the model parameters locally on each machine to minimize network communication. In practice, in order to reduce synchronization waiting time, these copies of the model are not necessarily updated in lock-steps, and can become stale. Despite much development in large-scale ML, the effect of staleness on the learning efficiency is inconclusive, mainly because it is challenging to control or monitor the staleness in complex distributed environments. In this work, we study the convergence behaviors of a wide array of ML models and algorithms under delayed updates. Our extensive experiments reveal the rich diversity of the effects of staleness on the convergence of ML algorithms, and offer insights into seemingly contradictory reports in the literature. The empirical findings also inspire a new convergence analysis of SGD in non-convex optimization under staleness, matching the best known convergence rate. |
| Stan | Stan is a probabilistic programming language implementing full Bayesian statistical inference wit MCMC sampling (NUTS, HMC) and penalized maximum likelihood estimation wit Optimization (L-BFGS. Stan is coded in C++ and runs on all major platforms (Linux, Mac, Windows). Stan is freedom-respecting, open-source software (new BSD core, GPLv3 interfaces). http://…/hello-stan.html rstan |
| Standard Methodology for Analytical Models (SMAM) |
In this document, the Standard Methodology for Analytical Models (SMAM) is described. The most frequent used methodology is the Cross Industrial Standard Processes for Data Mining (CRISP-DM), which has several shortcomings that translate into frequent friction points with the business when practitioners start building analytical models. |
| Stanford DAWN Project | Despite incredible recent advances in machine learning, building machine learning applications remains prohibitively time-consuming and expensive for all but the best-trained, best-funded engineering organizations. This expense comes not from a need for new and improved statistical models but instead from a lack of systems and tools for supporting end-to-end machine learning application development, from data preparation and labeling to productionization and monitoring. In this document, we outline opportunities for infrastructure supporting usable, end-to-end machine learning applications in the context of the nascent DAWN (Data Analytics for What’s Next) project at Stanford. |
| Stanford Question Answering Dataset (SQuAD) |
Stanford Question Answering Dataset (SQuAD) is a new reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage. With 100,000+ question-answer pairs on 500+ articles, SQuAD is significantly larger than previous reading comprehension datasets. |
| Stanza | The parameter server architecture is prevalently used for distributed deep learning. Each worker machine in a parameter server system trains the complete model, which leads to a hefty amount of network data transfer between workers and servers. We empirically observe that the data transfer has a non-negligible impact on training time. To tackle the problem, we design a new distributed training system called Stanza. Stanza exploits the fact that in many models such as convolution neural networks, most data exchange is attributed to the fully connected layers, while most computation is carried out in convolutional layers. Thus, we propose layer separation in distributed training: the majority of the nodes just train the convolutional layers, and the rest train the fully connected layers only. Gradients and parameters of the fully connected layers no longer need to be exchanged across the cluster, thereby substantially reducing the data transfer volume. We implement Stanza on PyTorch and evaluate its performance on Azure and EC2. Results show that Stanza accelerates training significantly over current parameter server systems: on EC2 instances with Tesla V100 GPU and 10Gb bandwidth for example, Stanza is 1.34x–13.9x faster for common deep learning models. |
| StarCraft II Learning Environment (SC2LE) |
This paper introduces SC2LE (StarCraft II Learning Environment), a reinforcement learning environment based on the StarCraft II game. This domain poses a new grand challenge for reinforcement learning, representing a more difficult class of problems than considered in most prior work. It is a multi-agent problem with multiple players interacting; there is imperfect information due to a partially observed map; it has a large action space involving the selection and control of hundreds of units; it has a large state space that must be observed solely from raw input feature planes; and it has delayed credit assignment requiring long-term strategies over thousands of steps. We describe the observation, action, and reward specification for the StarCraft II domain and provide an open source Python-based interface for communicating with the game engine. In addition to the main game maps, we provide a suite of mini-games focusing on different elements of StarCraft II gameplay. For the main game maps, we also provide an accompanying dataset of game replay data from human expert players. We give initial baseline results for neural networks trained from this data to predict game outcomes and player actions. Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain. On the mini-games, these agents learn to achieve a level of play that is comparable to a novice player. However, when trained on the main game, these agents are unable to make significant progress. Thus, SC2LE offers a new and challenging environment for exploring deep reinforcement learning algorithms and architectures. |
| Stark | This paper presents a new fast, highly scalable distributed matrix multiplication algorithm on Apache Spark, called Stark, based on Strassen’s matrix multiplication algorithm. Stark preserves Strassen’s 7 multiplications scheme in a distributed environment and thus achieves faster execution. It is based on two new ideas; it creates a recursion tree of computation where each level of such tree corresponds to division and combination of distributed matrix blocks in the form of Resilient Distributed Datasets(RDDs); It processes each divide and combine step in parallel and memorize the sub-matrices by intelligently tagging matrix blocks in it. To the best of our knowledge, Stark is the first Strassen’s implementation in Spark platform. We show experimentally that Stark has a strong scalability with increasing matrix size enabling us to multiply two (16384 x 16384) matrices with 28% and 36% less wall clock time than Marlin and MLLib respectively, state-of-the-art matrix multiplication approaches based on Spark. |
| StarKOSR | Motivated by many practical applications in logistics and mobility-as-a-service, we study the top-k optimal sequenced routes (KOSR) querying on large, general graphs where the edge weights may not satisfy the triangle inequality, e.g., road network graphs with travel times as edge weights. The KOSR querying strives to find the top-k optimal routes (i.e., with the top-k minimal total costs) from a given source to a given destination, which must visit a number of vertices with specific vertex categories (e.g., gas stations, restaurants, and shopping malls) in a particular order (e.g., visiting gas stations before restaurants and then shopping malls). To efficiently find the top-k optimal sequenced routes, we propose two algorithms PruningKOSR and StarKOSR. In PruningKOSR, we define a dominance relationship between two partially-explored routes. The partially-explored routes that can be dominated by other partially-explored routes are postponed being extended, which leads to a smaller searching space and thus improves efficiency. In StarKOSR, we further improve the efficiency by extending routes in an A* manner. With the help of a judiciously designed heuristic estimation that works for general graphs, the cost of partially explored routes to the destination can be estimated such that the qualified complete routes can be found early. In addition, we demonstrate the high extensibility of the proposed algorithms by incorporating Hop Labeling, an effective label indexing technique for shortest path queries, to further improve efficiency. Extensive experiments on multiple real-world graphs demonstrate that the proposed methods significantly outperform the baseline method. Furthermore, when k=1, StarKOSR also outperforms the state-of-the-art method for the optimal sequenced route queries. |
| StarNEig | In this paper, we present the StarNEig library for solving dense non-symmetric (generalized) eigenvalue problems. The library is built on top of the StarPU runtime system and targets both shared and distributed memory machines. Some components of the library support GPUs. The library is currently in an early beta state and only real arithmetic is supported. Support for complex data types is planned for a future release. This paper is aimed for potential users of the library. We describe the design choices and capabilities of the library, and contrast them to existing software such as ScaLAPACK. StarNEig implements a ScaLAPACK compatibility layer that should make it easy for a new user to transition to StarNEig. We demonstrate the performance of the library with a small set of computational experiments. |
| StarStar Model | Much time in process mining projects is spent on finding and understanding data sources and extracting the event data needed. As a result, only a fraction of time is spent actually applying techniques to discover, control and predict the business process. Moreover, there is a lack of techniques to display relationships on top of databases without the need to express a complex query to get the required information. In this paper, a novel modeling technique that works on top of databases is presented. This technique is able to show a multigraph representing activities inferred from database events, connected with edges that are annotated with frequency and performance information. The representation may be the entry point to apply advanced process mining techniques that work on classic event logs, as the model provides a simple way to retrieve a classic event log from a specified piece of model. Comparison with similar techniques and an empirical evaluation are provided. |
| StartNet | We propose StartNet to address Online Detection of Action Start (ODAS) where action starts and their associated categories are detected in untrimmed, streaming videos. Previous methods aim to localize action starts by learning feature representations that can directly separate the start point from its preceding background. It is challenging due to the subtle appearance difference near the action starts and the lack of training data. Instead, StartNet decomposes ODAS into two stages: action classification (using ClsNet) and start point localization (using LocNet). ClsNet focuses on per-frame labeling and predicts action score distributions online. Based on the predicted action scores of the past and current frames, LocNet conducts class-agnostic start detection by optimizing long-term localization rewards using policy gradient methods. The proposed framework is validated on two large-scale datasets, THUMOS’14 and ActivityNet. The experimental results show that StartNet significantly outperforms the state-of-the-art by 15%-30% p-mAP under the offset tolerance of 1-10 seconds on THUMOS’14, and achieves comparable performance on ActivityNet with 10 times smaller time offset. |
| Star-Transformer | Although the fully-connected attention-based model Transformer has achieved great successes on many NLP tasks, it has heavy structure and usually requires large training data. In this paper, we present the Star-Transformer, an alternative and light-weighted model of the Transformer. To reduce the model complexity, we replace the fully-connected structure with a star-shaped structure, in which every two non-adjacent nodes are connected through a shared relay node. Thus, the Star-Transformer has lower complexity than the standard Transformer (from quadratic to linear according to the input length) and preserves the ability to handle with the long-range dependencies. The experiments on four tasks (22 datasets) show the Star-Transformer achieved significant improvements against the standard Transformer for the modestly sized datasets. |
| STARTS | Although researchers in clinical psychology routinely gather data in which many individuals respond at multiple times, there is not a standard way to analyze such data. A new approach for the analysis of such data is described. It is proposed that a person’s current standing on a variable is caused by 3 sources of variance: a term that does not change (trait), a term that changes (state), and a random term (error). It is shown how structural equation modeling can be used to estimate such a model. An extended example is presented in which the correlations between variables are quite different at the trait, state, and error levels. (PsycINFO Database Record (c) 2016 APA, all rights reserved) STARTS |
| Stata | Stata is a complete, integrated statistical software package that provides everything you need for data analysis, data management, and graphics. With both a point-and-click interface and a powerful, intuitive command syntax, Stata is fast, accurate, and easy to use. All analyses can be reproduced and documented for publication and review. Version control ensures statistical programs will continue to produce the same results no matter when you wrote them. |
| State- and Static Output-Feedback Generalized Guaranteed Cost Control | In this paper, we propose state- and static output-feedback generalized guaranteed cost control (GCC) approaches for discrete-time linear systems subject to norm-bounded structured parametric uncertainties. This method enables the convex synthesis for a more general class of systems, where uncertainties are uncorrelated block diagonal, and no feed-through uncertainty is multiplicative with control input ones. It also provides necessary and sufficient conditions for state-feedback and sufficient conditions for static output-feedback. We also present a comparative study of the proposed controllers, standard Linear Quadratic Regulator, and GCC found in the literature. |
| State Refinement Module for LSTM Network (SR-LSTM) |
In crowd scenarios, reliable trajectory prediction of pedestrians requires insightful understanding of their social behaviors. These behaviors have been well investigated by plenty of studies, while it is hard to be fully expressed by hand-craft rules. Recent studies based on LSTM networks have shown great ability to learn social behaviors. However, many of these methods rely on previous neighboring hidden states but ignore the important current intention of the neighbors. In order to address this issue, we propose a data-driven state refinement module for LSTM network (SR-LSTM), which activates the utilization of the current intention of neighbors, and jointly and iteratively refines the current states of all participants in the crowd through a message passing mechanism. To effectively extract the social effect of neighbors, we further introduce a social-aware information selection mechanism consisting of an element-wise motion gate and a pedestrian-wise attention to select useful message from neighboring pedestrians. Experimental results on two public datasets, i.e. ETH and UCY, demonstrate the effectiveness of our proposed SR-LSTM and we achieves state-of-the-art results. |
| State Representation Learning | State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning using generic priors on the state characteristics. S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning |
| State Space Model (SSM) |
State space model (SSM) refers to a class of probabilistic graphical model (Koller and Friedman, 2009) that describes the probabilistic dependence between the latent state variable and the observed measurement. The state or the measurement can be either continuous or discrete. The term “state space” originated in 1960s in the area of control engineering (Kalman, 1960). SSM provides a general framework for analyzing deterministic and stochastic dynamical systems that are measured or observed through a stochastic process. The SSM framework has been successfully applied in engineering, statistics, computer science and economics to solve a broad range of dynamical systems problems. Other terms used to describe SSMs are hidden Markov models (HMMs) (Rabiner, 1989) and latent process models. The most well studied SSM is the Kalman filter, which defines an optimal algorithm for inferring linear Gaussian systems. |
| State-Action-Reward-State-Action (SARSA) |
SARSA (State-Action-Reward-State-Action) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning area of machine learning. It was introduced in a technical note where the alternative name SARSA was only mentioned as a footnote. This name simply reflects the fact that the main function for updating the Q-value depends on the current state of the agent “S1”, the action the agent chooses “A1”, the reward “R” the agent gets for choosing this action, the state “S2” that the agent will now be in after taking that action, and finally the next action “A2” the agent will choose in its new state. Taking every letter in the quintuple (st, at, rt, st+1, at+1) yields the word SARSA. |
| Stated Preference Method | The term “Stated Preference Methods” refers to a family of techniques which use individual respondents´ statements about their preferences in a set of options to estimate utility functions. The options are typically descriptions of situations or contexts constructed by the researcher. By their nature, stated preference methods require purpose-designed surveys for their collection of data. “Contingent Valuation” is often referred to as a stated preference model. http://…/spmur |
| State-Denoised Recurrent Neural Network (SDRNN) |
Recurrent neural networks (RNNs) are difficult to train on sequence processing tasks, not only because input noise may be amplified through feedback, but also because any inaccuracy in the weights has similar consequences as input noise. We describe a method for denoising the hidden state during training to achieve more robust representations thereby improving generalization performance. Attractor dynamics are incorporated into the hidden state to `clean up’ representations at each step of a sequence. The attractor dynamics are trained through an auxillary denoising loss to recover previously experienced hidden states from noisy versions of those states. This state-denoised recurrent neural network {SDRNN} performs multiple steps of internal processing for each external sequence step. On a range of tasks, we show that the SDRNN outperforms a generic RNN as well as a variant of the SDRNN with attractor dynamics on the hidden state but without the auxillary loss. We argue that attractor dynamics—and corresponding connectivity constraints—are an essential component of the deep learning arsenal and should be invoked not only for recurren |