Deep Neural Linear Bandit
We study the neural-linear bandit model for solving sequential decision-making problems with high dimensional side information. Neural-linear bandits leverage the representation power of deep neural networks and combine it with efficient exploration mechanisms, designed for linear contextual bandits, on top of the last hidden layer. Since the representation is being optimized during learning, information regarding exploration with ‘old’ features is lost. Here, we propose the first limited memory neural-linear bandit that is resilient to this phenomenon, which we term catastrophic forgetting. We evaluate our method on a variety of real-world data sets, including regression, classification, and sentiment analysis, and observe that our algorithm is resilient to catastrophic forgetting and achieves superior performance. …

Emotional Word Vector (EVEC)
It is important for machines to interpret human emotions properly for better human-machine communications, as emotion is an essential part of human-to-human communications. One aspect of emotion is reflected in the language we use. How to represent emotions in texts is a challenge in natural language processing (NLP). Although continuous vector representations like word2vec have become the new norm for NLP problems, their limitations are that they do not take emotions into consideration and can unintentionally contain bias toward certain identities like different genders. This thesis focuses on improving existing representations in both word and sentence levels by explicitly taking emotions inside text and model bias into account in their training process. Our improved representations can help to build more robust machine learning models for affect-related text classification like sentiment/emotion analysis and abusive language detection. We first propose representations called emotional word vectors (EVEC), which is learned from a convolutional neural network model with an emotion-labeled corpus, which is constructed using hashtags. Secondly, we extend to learning sentence-level representations with a huge corpus of texts with the pseudo task of recognizing emojis. Our results show that, with the representations trained from millions of tweets with weakly supervised labels such as hashtags and emojis, we can solve sentiment/emotion analysis tasks more effectively. Lastly, as examples of model bias in representations of existing approaches, we explore a specific problem of automatic detection of abusive language. We address the issue of gender bias in various neural network models by conducting experiments to measure and reduce those biases in the representations in order to build more robust classification models. …

Waterfall Chart
A waterfall chart is a form of data visualization that helps in understanding the cumulative effect of sequentially introduced positive or negative values. The waterfall chart is also known as a flying bricks chart or Mario chart due to the apparent suspension of columns (bricks) in mid-air. Often in finance, it will be referred to as a bridge. Waterfall charts were popularized by the strategic consulting firm McKinsey & Company in its presentations to clients. The waterfall chart is normally used for understanding how an initial value is affected by a series of intermediate positive or negative values. Usually the initial and the final values are represented by whole columns, while the intermediate values are denoted by floating columns. The columns are color-coded for distinguishing between positive and negative values.
➘ “Waterfall Chart”
Understanding Waterfall Plots
Waterfall plots – what and how? …

Attentive Dense Graph Propagation Module (ADGPM)
The potential of graph convolutional neural networks for the task of zero-shot learning has been demonstrated recently. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization to new classes when faced with a lack of data. However, knowledge from distant nodes can get diluted when propagating through intermediate nodes, because current approaches to zero-shot learning use graph propagation schemes that perform Laplacian smoothing at each layer. We show that extensive smoothing does not help the task of regressing classifier weights in zero-shot learning. In order to still incorporate information from distant nodes and utilize the graph structure, we propose an Attentive Dense Graph Propagation Module (ADGPM). ADGPM allows us to exploit the hierarchical graph structure of the knowledge graph through additional connections. These connections are added based on a node’s relationship to its ancestors and descendants and an attention scheme is further used to weigh their contribution depending on the distance to the node. Finally, we illustrate that finetuning of the feature representation after training the ADGPM leads to considerable improvements. Our method achieves competitive results, outperforming previous zero-shot learning approaches. …

FPDeep
Deep Neural Networks (DNNs) have revolutionized numerous applications, but the demand for ever more performance remains unabated. Scaling DNN computations to larger clusters is generally done by distributing tasks in batch mode using methods such as distributed synchronous SGD. Among the issues with this approach is that to make the distributed cluster work with high utilization, the workload distributed to each node must be large, which implies nontrivial growth in the SGD mini-batch size. In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer parallelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is a fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation. As a result, storage demand is reduced to the point where only on-chip memory is used for the convolution layers. We evaluate FPDeep with the Alexnet, VGG-16, and VGG-19 benchmarks. Experimental results show that FPDeep has good scalability to a large number of FPGAs, with the limiting factor being the FPGA-to-FPGA bandwidth. With 6 transceivers per FPGA, FPDeep shows linearity up to 83 FPGAs. Energy efficiency is evaluated with respect to GOPs/J. FPDeep provides, on average, 6.36x higher energy efficiency than comparable GPU servers. …

Directed Acyclic Graph (DAG)
In mathematics and computer science, a directed acyclic graph (DAG), is a directed graph with no directed cycles. That is, it is formed by a collection of vertices and directed edges, each edge connecting one vertex to another, such that there is no way to start at some vertex v and follow a sequence of edges that eventually loops back to v again. …

Google Cloud Dataflow
Simplified stream and batch data processing, with equal reliability and expressiveness. Cloud Dataflow is a fully-managed service for transforming and enriching data in stream (real time) and batch (historical) modes with equal reliability and expressiveness — no more complex workarounds or compromises needed. And with its serverless approach to resource provisioning and management, you have access to virtually limitless capacity to solve your biggest data processing challenges, while paying only for what you use. Cloud Dataflow unlocks transformational use cases across industries, including:
· check Clickstream, Point-of-Sale, and segmentation analysis in retail
· check Fraud detection in financial services
· check Personalized user experience in gaming
· check IoT analytics in manufacturing, healthcare, and logistics …

Stochastic Quantized Activation Distribution (SQUAD)
High-risk domains require reliable confidence estimates from predictive models. Deep latent variable models provide these, but suffer from the rigid variational distributions used for tractable inference, which err on the side of overconfidence. We propose Stochastic Quantized Activation Distributions (SQUAD), which imposes a flexible yet tractable distribution over discretized latent variables. The proposed method is scalable, self-normalizing and sample efficient. We demonstrate that the model fully utilizes the flexible distribution, learns interesting non-linearities, and provides predictive uncertainty of competitive quality. …

Texture Effects Transfer GAN (TET-GAN)
Text effects transfer technology automatically makes the text dramatically more impressive. However, previous style transfer methods either study the model for general style, which cannot handle the highly-structured text effects along the glyph, or require manual design of subtle matching criteria for text effects. In this paper, we focus on the use of the powerful representation abilities of deep neural features for text effects transfer. For this purpose, we propose a novel Texture Effects Transfer GAN (TET-GAN), which consists of a stylization subnetwork and a destylization subnetwork. The key idea is to train our network to accomplish both the objective of style transfer and style removal, so that it can learn to disentangle and recombine the content and style features of text effects images. To support the training of our network, we propose a new text effects dataset with as much as 64 professionally designed styles on 837 characters. We show that the disentangled feature representations enable us to transfer or remove all these styles on arbitrary glyphs using one network. Furthermore, the flexible network design empowers TET-GAN to efficiently extend to a new text style via one-shot learning where only one example is required. We demonstrate the superiority of the proposed method in generating high-quality stylized text over the state-of-the-art methods. …

Large-Scale Information Network Embedding (LINE)
This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction. Most existing graph embedding methods do not scale for real world information networks which usually contain millions of nodes. In this paper, we propose a novel network embedding method called the ‘LINE,’ which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted. The method optimizes a carefully designed objective function that preserves both the local and global network structures. An edge-sampling algorithm is proposed that addresses the limitation of the classical stochastic gradient descent and improves both the effectiveness and the efficiency of the inference. Empirical experiments prove the effectiveness of the LINE on a variety of real-world information networks, including language networks, social networks, and citation networks. The algorithm is very efficient, which is able to learn the embedding of a network with millions of vertices and billions of edges in a few hours on a typical single machine. The source code of the LINE is available online. …

Determinized Sparse Partially Observable Tree (DESPOT)
The partially observable Markov decision process (POMDP) provides a principled general framework for planning under uncertainty, but solving POMDPs optimally is computationally intractable, due to the ‘curse of dimensionality’ and the ‘curse of history’. To overcome these challenges, we introduce the Determinized Sparse Partially Observable Tree (DESPOT), a sparse approximation of the standard belief tree, for online planning under uncertainty. A DESPOT focuses online planning on a set of randomly sampled scenarios and compactly captures the ‘execution’ of all policies under these scenarios. We show that the best policy obtained from a DESPOT is near-optimal, with a regret bound that depends on the representation size of the optimal policy. Leveraging this result, we give an anytime online planning algorithm, which searches a DESPOT for a policy that optimizes a regularized objective function. Regularization balances the estimated value of a policy under the sampled scenarios and the policy size, thus avoiding overfitting. The algorithm demonstrates strong experimental results, compared with some of the best online POMDP algorithms available. It has also been incorporated into an autonomous driving system for realtime vehicle control. …

Support Vector Machine (SVM)
In machine learning, support vector machines (SVMs, also support vector networks) are supervised learning models with associated learning algorithms that analyze data and recognize patterns, used for classification and regression analysis. Given a set of training examples, each marked as belonging to one of two categories, an SVM training algorithm builds a model that assigns new examples into one category or the other, making it a non-probabilistic binary linear classifier. An SVM model is a representation of the examples as points in space, mapped so that the examples of the separate categories are divided by a clear gap that is as wide as possible. New examples are then mapped into that same space and predicted to belong to a category based on which side of the gap they fall on. …

AutoEncoder Feature Selector (AEFS)
High-dimensional data in many areas such as computer vision and machine learning brings in computational and analytical difficulty. Feature selection which select a subset of features from original ones has been proven to be effective and efficient to deal with high-dimensional data. In this paper, we propose a novel AutoEncoder Feature Selector (AEFS) for unsupervised feature selection. AEFS is based on the autoencoder and the group lasso regularization. Compared to traditional feature selection methods, AEFS can select the most important features in spite of nonlinear and complex correlation among features. It can be viewed as a nonlinear extension of the linear method regularized self-representation (RSR) for unsupervised feature selection. In order to deal with noise and corruption, we also propose robust AEFS. An efficient iterative algorithm is designed for model optimization and experimental results verify the effectiveness and superiority of the proposed method. …

Functional Intrusive Load Monitor (FILM)
Non-Intrusive Load Monitoring (NILM) is an important application to monitor household appliance activities and provide related information to house owner or/and utility company via a single sensor installed at the electrical entry of the house. It can be used for different purposes in residential and industrial sectors. Thus, an increasing number of new algorithms have been developed in recent years. In these algorithms, researchers either use existing public datasets or collect their own data which causes such problems as insufficiency of electrical parameters, missing of ground-truth data, absence of many appliances, and lack of appliance information. To solve these problems, this paper presents a model-based platform for NILM system development, namely Functional Intrusive Load Monitor (FILM). By using this platform, the state transitions and activities of all the involved appliances can be preset by researchers, and multiple electrical parameters such as harmonics and power factor can be monitored or calculated. This platform will help researchers save the time of collecting experimental data, utilize precise control of individual appliance activities, and develop load signatures of devices. This paper describes the steps, structure, and requirements of building this platform. Case study is presented to help understand this platform. …

Quaternion Long-Short Term Memory (QLSTM)
Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition tasks, due to their efficient representation of long and short term dependencies in sequences of inter-dependent features. Nonetheless, internal dependencies within the element composing multidimensional features are weakly considered by traditional real-valued representations. We propose a novel quaternion long-short term memory (QLSTM) recurrent neural network that takes into account both the external relations between the features composing a sequence, and these internal latent structural dependencies with the quaternion algebra. QLSTMs are compared to LSTMs during a memory copy-task and a realistic application of speech recognition on the Wall Street Journal (WSJ) dataset. QLSTM reaches better performances during the two experiments with up to $2.8$ times less learning parameters, leading to a more expressive representation of the information. …

Cautious Deep Learning
Most classifiers operate by selecting the maximum of an estimate of the conditional distribution $p(y|x)$ where $x$ stands for the features of the instance to be classified and $y$ denotes its label. This often results in a hubristic bias: overconfidence in the assignment of a definite label. Usually, the observations are concentrated on a small volume but the classifier provides definite predictions for the entire space. We propose constructing conformal prediction sets [vovk2005algorithmic] which contain a set of labels rather than a single label. These conformal prediction sets contain the true label with probability $1-\alpha$. Our construction is based on $p(x|y)$ rather than $p(y|x)$ which results in a classifier that is very cautious: it outputs the null set – meaning `I don’t know’ — when the object does not resemble the training examples. An important property of our approach is that classes can be added or removed without having to retrain the classifier. We demonstrate the performance on the ImageNet ILSVRC dataset using high dimensional features obtained from state of the art convolutional neural networks. …

Data Standardization
When approaching data for modeling, some standard procedures should be used to prepare the data for modeling:
1.First the data should be filtered, and any outliers removed from the data (watch for a future post on how to scrub your raw data removing only legitimate outliers).
2.The data should be normalized or standardized to bring all of the variables into proportion with one another. For example, if one variable is 100 times larger than another (on average), then your model may be better behaved if you normalize/standardize the two variables to be approximately equivalent. Technically though, whether normalized/standardized, the coefficients associated with each variable will scale appropriately to adjust for the disparity in the variable sizes. …

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. …

Rant
Rant is an all-purpose procedural text engine that is most simply described as the opposite of Regex. It has been refined to include a dizzying array of features for handling everything from the most basic of string generation tasks to advanced dialogue generation, code templating, automatic formatting, and more. The goal of the project is to enable developers of all kinds to automate repetitive writing tasks with a high degree of creative freedom. …

Mask Editor
Deep convolutional neural network (DCNN) is the state-of-the-art method for image segmentation, which is one of key challenging computer vision tasks. However, DCNN requires a lot of training images with corresponding image masks to get a good segmentation result. Image annotation software which is easy to use and allows fast image mask generation is in great demand. To the best of our knowledge, all existing image annotation software support only drawing bounding polygons, bounding boxes, or bounding ellipses to mark target objects. These existing software are inefficient when targeting objects that have irregular shapes (e.g., defects in fabric images or tire images). In this paper we design an easy-to-use image annotation software called Mask Editor for image mask generation. Mask Editor allows drawing any bounding curve to mark objects and improves efficiency to mark objects with irregular shapes. Mask Editor also supports drawing bounding polygons, drawing bounding boxes, drawing bounding ellipses, painting, erasing, super-pixel-marking, image cropping, multi-class masks, mask loading, and mask modifying. …

Phaedra
Phaedra is an open source platform for data capture and analysis of high-content screening data. It offers functionality to
· import image data from any source
· assess your data with industry’s richest toolbox
· improve data quality using intelligent validation methods
· use built-in statistics and machine learning workflows
· generate QC and analysis reports using templates …

Generalizable Approaching Policy LEarning (GAPLE)
We study the problem of learning a generalizable action policy for an intelligent agent to actively approach an object of interest in indoor environment solely from its visual inputs. While scene-driven or recognition-driven visual navigation has been widely studied, prior efforts suffer severely from the limited generalization capability. In this paper, we first argue the object searching task is environment dependent while the approaching ability is general. To learn a generalizable approaching policy, we present a novel solution dubbed as GAPLE which adopts two channels of visual features: depth and semantic segmentation, as the inputs to the policy learning module. The empirical studies conducted on the House3D dataset as well as on a physical platform in a real world scenario validate our hypothesis, and we further provide in-depth qualitative analysis. …

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? …

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. …

Highly Efficient Network (HENet)
In order to enhance the real-time performance of convolutional neural networks(CNNs), more and more researchers are focusing on improving the efficiency of CNN. Based on the analysis of some CNN architectures, such as ResNet, DenseNet, ShuffleNet and so on, we combined their advantages and proposed a very efficient model called Highly Efficient Networks(HENet). The new architecture uses an unusual way to combine group convolution and channel shuffle which was mentioned in ShuffleNet. Inspired by ResNet and DenseNet, we also proposed a new way to use element-wise addition and concatenation connection with each block. In order to make greater use of feature maps, pooling operations are removed from HENet. The experiments show that our model’s efficiency is more than 1 times higher than ShuffleNet on many open source datasets, such as CIFAR-10/100 and SVHN. …

Information-Theoretic Canonical Correlation Analysis (ITCCA)
Canonical Correlation Analysis (CCA) is a linear representation learning method that seeks maximally correlated variables in multi-view data. Non-linear CCA extends this notion to a broader family of transformations, which are more powerful for many real-world applications. Given the joint probability, the Alternating Conditional Expectation (ACE) provides an optimal solution to the non-linear CCA problem. However, it suffers from limited performance and an increasing computational burden when only a finite number of observations is available. In this work we introduce an information-theoretic framework for the non-linear CCA problem (ITCCA), which extends the classical ACE approach. Our suggested framework seeks compressed representations of the data that allow a maximal level of correlation. This way we control the trade-off between the flexibility and the complexity of the representation. Our approach demonstrates favorable performance at a reduced computational burden, compared to non-linear alternatives, in a finite sample size regime. Further, ITCCA provides theoretical bounds and optimality conditions, as we establish fundamental connections to rate-distortion theory, the information bottleneck and remote source coding. In addition, it implies a ‘soft’ dimensionality reduction, as the compression level is measured (and governed) by the mutual information between the original noisy data and the signals that we extract. …

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. …

Dynamic Chain Event Graph (DCEG)
Chain Event Graphs (CEGs) have been a useful class of tree-based graphical models especially designed to capture context-specific conditional independences. However, it has became increasingly apparent that in many contexts modelling variable changes explicitly over time provide better results. Only very recently such dynamic CEG was defined in the literature. In this paper we introduce a dynamic version of CEGs to model longitudinal discrete processes observed over discrete time intervals that have highly asymmetric developments and context-specific structures. We discuss some limitations of the approach that directly extends the semantics of CEGs to dynamic settings. Finally, an example of multivariate processes describing a dynamic radicalisation process of inmates in a prison is used to show how to reason with a dynamic CEG.
An N Time-Slice Dynamic Chain Event Graph …

Learning through Probing (LTP)
Multi-agent reinforcement learning has received significant interest in recent years notably due to the advancements made in deep reinforcement learning which have allowed for the developments of new architectures and learning algorithms. Using social dilemmas as the training ground, we present a novel learning architecture, Learning through Probing (LTP), where agents utilize a probing mechanism to incorporate how their opponent’s behavior changes when an agent takes an action. We use distinct training phases and adjust rewards according to the overall outcome of the experiences accounting for changes to the opponents behavior. We introduce a parameter eta to determine the significance of these future changes to opponent behavior. When applied to the Iterated Prisoner’s Dilemma (IPD), LTP agents demonstrate that they can learn to cooperate with each other, achieving higher average cumulative rewards than other reinforcement learning methods while also maintaining good performance in playing against static agents that are present in Axelrod tournaments. We compare this method with traditional reinforcement learning algorithms and agent-tracking techniques to highlight key differences and potential applications. We also draw attention to the differences between solving games and societal-like interactions and analyze the training of Q-learning agents in makeshift societies. This is to emphasize how cooperation may emerge in societies and demonstrate this using environments where interactions with opponents are determined through a random encounter format of the IPD. …

Stochastic Approximation of Expectation Maximization (SAEM)
The SAEM algorithm: – computes the maximum likelihood estimator of the population parameters, without any approximation of the model (linearisation, quadrature approximation,…), using the Stochastic Approximation Expectation Maximization (SAEM) algorithm, – provides standard errors for the maximum likelihood estimator – estimates the conditional modes, the conditional means and the conditional standard deviations of the individual parameters, using the Hastings-Metropolis algorithm. Several applications of SAEM in agronomy, animal breeding and PKPD analysis have been published by members of the Monolix group (http://group.monolix.org ). …