Mixture Hyper Long Short Term Memory Network
Classifying human cognitive states from behavioral and physiological signals is a challenging problem with important applications in robotics. The problem is challenging due to the data variability among individual users, and sensor artefacts. In this work, we propose an end-to-end framework for real-time cognitive workload classification with mixture Hyper Long Short Term Memory Networks, a novel variant of HyperNetworks. Evaluating the proposed approach on an eye-gaze pattern dataset collected from simulated driving scenarios of different cognitive demands, we show that the proposed framework outperforms previous baseline methods and achieves 83.9\% precision and 87.8\% recall during test. We also demonstrate the merit of our proposed architecture by showing improved performance over other LSTM-based methods. …

Adaptive Automatic Threat Recognition (AATR)
This work addresses the question whether it is possible to design a computer-vision based automatic threat recognition (ATR) system so that it can adapt to changing specifications of a threat without having to create a new ATR each time. The changes in threat specifications, which may be warranted by intelligence reports and world events, are typically regarding the physical characteristics of what constitutes a threat: its material composition, its shape, its method of concealment, etc. Here we present our design of an AATR system (Adaptive ATR) that can adapt to changing specifications in materials characterization (meaning density, as measured by its x-ray attenuation coefficient), its mass, and its thickness. Our design uses a two-stage cascaded approach, in which the first stage is characterized by a high recall rate over the entire range of possibilities for the threat parameters that are allowed to change. The purpose of the second stage is to then fine-tune the performance of the overall system for the current threat specifications. The computational effort for this fine-tuning for achieving a desired PD/PFA rate is far less than what it would take to create a new classifier with the same overall performance for the new set of threat specifications. …

Partially Labeled Degree-Corrected Block Model (pDCBM)
Community detection was a hot topic on network analysis, where the main aim is to perform unsupervised learning or clustering in networks. Recently, semi-supervised learning has received increasing attention among researchers. In this paper, we propose a new algorithm, called weighted inverse Laplacian (WIL), for predicting labels in partially labeled networks. The idea comes from the first hitting time in random walk, and it also has nice explanations both in information propagation and the regularization framework. We propose a partially labeled degree-corrected block model (pDCBM) to describe the generation of partially labeled networks. We show that WIL ensures the misclassification rate is of order $O(\frac{1}{d})$ for the pDCBM with average degree $d=\Omega(\log n),$ and that it can handle situations with greater unbalanced than traditional Laplacian methods. WIL outperforms other state-of-the-art methods in most of our simulations and real datasets, especially in unbalanced networks and heterogeneous networks. …

NVIDIA Data Loading Library (DALI)
Today’s deep learning applications include complex, multi-stage pre-processing data pipelines that include compute-intensive steps mainly carried out on the CPU. For instance, steps such as load data from disk, decode, crop, random resize, color and spatial augmentations and format conversions are carried out on the CPUs, limiting the performance and scalability of training and inference tasks. In addition, the deep learning frameworks today have multiple data pre-processing implementations, resulting in challenges such as portability of training and inference workflows and code maintainability. NVIDIA Data Loading Library (DALI) is a collection of highly optimized building blocks and an execution engine to accelerate input data pre-processing for deep learning applications. DALI provides both performance and flexibility of accelerating different data pipelines, as a single library, that can be easily integrated into different deep learning training and inference applications. …

Progressively Growing Generative Autoencoder (PIONEER,Pioneer Network)
We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, but they cannot reconstruct existing images. Previous works have attempted to extend GANs to support such inference but, so far, have not delivered satisfactory high-quality results. Instead, we propose the Progressively Growing Generative Autoencoder (PIONEER) network which achieves high-quality reconstruction with $128{\times}128$ images without requiring a GAN discriminator. We merge recent techniques for progressively building up the parts of the network with the recently introduced adversarial encoder-generator network. The ability to reconstruct input images is crucial in many real-world applications, and allows for precise intelligent manipulation of existing images. We show promising results in image synthesis and inference, with state-of-the-art results in CelebA inference tasks. …

Computational Productive Laziness (CPL)
In artificial intelligence (AI) mediated workforce management systems (e.g., crowdsourcing), long-term success depends on workers accomplishing tasks productively and resting well. This dual objective can be summarized by the concept of productive laziness. Existing scheduling approaches mostly focus on efficiency but overlook worker wellbeing through proper rest. In order to enable workforce management systems to follow the IEEE Ethically Aligned Design guidelines to prioritize worker wellbeing, we propose a distributed Computational Productive Laziness (CPL) approach in this paper. It intelligently recommends personalized work-rest schedules based on local data concerning a worker’s capabilities and situational factors to incorporate opportunistic resting and achieve superlinear collective productivity without the need for explicit coordination messages. Extensive experiments based on a real-world dataset of over 5,000 workers demonstrate that CPL enables workers to spend 70% of the effort to complete 90% of the tasks on average, providing more ethically aligned scheduling than existing approaches. …

Graph Variogram
Irregularly sampling a spatially stationary random field does not yield a graph stationary signal in general. Based on this observation, we build a definition of graph stationarity based on intrinsic stationarity, a less restrictive definition of classical stationarity. We introduce the concept of graph variogram, a novel tool for measuring spatial intrinsic stationarity at local and global scales for irregularly sampled signals by selecting subgraphs of local neighborhoods. Graph variograms are extensions of variograms used for signals defined on continuous Euclidean space. Our experiments with intrinsically stationary signals sampled on a graph, demonstrate that graph variograms yield estimates with small bias of true theoretical models, while being robust to sampling variation of the space. …

OSEMN Process (OSEMN)
We’ve variously heard it said that data science requires some command-line fu for data procurement and preprocessing, or that one needs to know some machine learning or stats, or that one should know how to `look at data’. All of these are partially true, so we thought it would be useful to propose one possible taxonomy – we call it the Snice* taxonomy – of what a data scientist does, in roughly chronological order:
· Obtain
· Scrub
· Explore
· Model
· iNterpret
(or, if you like, OSEMN, which rhymes with possum).
Using the OSEMN Process to Work Through a Data Problem …

Bayesian Patchwork
Doctors often rely on their past experience in order to diagnose patients. For a doctor with enough experience, almost every patient would have similarities to key cases seen in the past, and each new patient could be viewed as a mixture of these key past cases. Because doctors often tend to reason this way, an efficient computationally aided diagnostic tool that thinks in the same way might be helpful in locating key past cases of interest that could assist with diagnosis. This article develops a novel mathematical model to mimic the type of logical thinking that physicians use when considering past cases. The proposed model can also provide physicians with explanations that would be similar to the way they would naturally reason about cases. The proposed method is designed to yield predictive accuracy, computational efficiency, and insight into medical data; the key element is the insight into medical data, in some sense we are automating a complicated process that physicians might perform manually. We finally implemented the result of this work on two publicly available healthcare datasets, for heart disease prediction and breast cancer prediction. …

MESH
With the rapid growth of large online social networks, the ability to analyze large-scale social structure and behavior has become critically important, and this has led to the development of several scalable graph processing systems. In reality, however, social interaction takes place not only between pairs of individuals as in the graph model, but rather in the context of multi-user groups. Research has shown that such group dynamics can be better modeled through a more general hypergraph model, resulting in the need to build scalable hypergraph processing systems. In this paper, we present MESH, a flexible distributed framework for scalable hypergraph processing. MESH provides an easy-to-use and expressive application programming interface that naturally extends the think like a vertex model common to many popular graph processing systems. Our framework provides a flexible implementation based on an underlying graph processing system, and enables different design choices for the key implementation issues of partitioning a hypergraph representation. We implement MESH on top of the popular GraphX graph processing framework in Apache Spark. Using a variety of real datasets and experiments conducted on a local 8-node cluster as well as a 65-node Amazon AWS testbed, we demonstrate that MESH provides flexibility based on data and application characteristics, as well as scalability with cluster size. We further show that it is competitive in performance to HyperX, another hypergraph processing system based on Spark, while providing a much simpler implementation (requiring about 5X fewer lines of code), thus showing that simplicity and flexibility need not come at the cost of performance. …

Quantized Neural Network (QNN)
We introduce a method to train Quantized Neural Networks (QNNs) — neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing the parameter gradients. During the forward pass, QNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations. As a result, power consumption is expected to be drastically reduced. We trained QNNs over the MNIST, CIFAR-10, SVHN and ImageNet datasets. The resulting QNNs achieve prediction accuracy comparable to their 32-bit counterparts. For example, our quantized version of AlexNet with 1-bit weights and 2-bit activations achieves 51% top-1 accuracy. Moreover, we quantize the parameter gradients to 6-bits as well which enables gradients computation using only bit-wise operation. Quantized recurrent neural networks were tested over the Penn Treebank dataset, and achieved comparable accuracy as their 32-bit counterparts using only 4-bits. Last but not least, we programmed a binary matrix multiplication GPU kernel with which it is possible to run our MNIST QNN 7 times faster than with an unoptimized GPU kernel, without suffering any loss in classification accuracy. The QNN code is available online. …

Tofu
There is a trend towards using very large deep neural networks (DNN) to improve the accuracy of complex machine learning tasks. However, the size of DNN models that can be explored today is limited by the amount of GPU device memory. This paper presents Tofu, a system for partitioning very large DNN models across multiple GPU devices. Tofu is designed for a tensor-based dataflow system: for each operator in the dataflow graph, it partitions its input/output tensors and parallelizes its execution across workers. Tofu can automatically discover how each operator can be partitioned by analyzing its semantics expressed in a simple specification language. Tofu uses a search algorithm based on dynamic programming to determine the best partition strategy for each operator in the entire dataflow graph. Our experiments on an 8-GPU machine show that Tofu enables the training of very large CNN and RNN models. It also achieves better performance than alternative approaches to train very large models on multiple GPUs. …

Gradient Confusion
The goal of this paper is to study why stochastic gradient descent (SGD) is efficient for neural networks, and how neural net design affects SGD. In particular, we investigate how overparameterization — an increase in the number of parameters beyond the number of training data — affects the dynamics of SGD. We introduce a simple concept called gradient confusion. When confusion is high, stochastic gradients produced by different data samples may be negatively correlated, slowing down convergence. But when gradient confusion is low, we show that SGD has better convergence properties than predicted by classical theory. Using theoretical and experimental results, we study how overparameterization affects gradient confusion, and thus the convergence of SGD, on linear models and neural networks. We show that increasing the number of parameters of linear models or increasing the width of neural networks leads to lower gradient confusion, and thus faster and easier model training. We also show how overparameterization by increasing the depth of neural networks results in higher gradient confusion, making deeper models harder to train. Finally, we observe empirically that techniques like batch normalization and skip connections reduce gradient confusion, which helps reduce the training burden of deep networks. …

ChainGAN
We propose a new architecture and training methodology for generative adversarial networks. Current approaches attempt to learn the transformation from a noise sample to a generated data sample in one shot. Our proposed generator architecture, called $\textit{ChainGAN}$, uses a two-step process. It first attempts to transform a noise vector into a crude sample, similar to a traditional generator. Next, a chain of networks, called $\textit{editors}$, attempt to sequentially enhance this sample. We train each of these units independently, instead of with end-to-end backpropagation on the entire chain. Our model is robust, efficient, and flexible as we can apply it to various network architectures. We provide rationale for our choices and experimentally evaluate our model, achieving competitive results on several datasets. …

LOBO
Botnets in online social networks are increasingly often affecting the regular flow of discussion, attacking regular users and their posts, spamming them with irrelevant or offensive content, and even manipulating the popularity of messages and accounts. Researchers and cybercriminals are involved in an arms race, and new and updated botnets designed to defeat current detection systems are constantly developed, rendering such detection systems obsolete. In this paper, we motivate the need for a generalized evaluation in Twitter bot detection and propose a methodology to evaluate bot classifiers by testing them on unseen bot classes. We show that this methodology is empirically robust, using bot classes of varying sizes and characteristics and reaching similar results, and argue that methods trained and tested on single bot classes or datasets might not able to generalize to new bot classes. We train one such classifier on over 200,000 data points and show that it achieves over 97% accuracy. The data used to train and test this classifier includes some of the largest and most varied collections of bots used in literature. We then test this theoretically sound classifier using our methodology, highlighting that it does not generalize well to unseen bot classes. Finally, we discuss the implications of our results, and reasons why some bot classes are easier and faster to detect than others. …

ResUNet-a
Scene understanding of high resolution aerial images is of great importance for the task of automated monitoring in various remote sensing applications. Due to the large within-class and small between-class variance in pixel values of objects of interest, this remains a challenging task. In recent years, deep convolutional neural networks have started being used in remote sensing applications and demonstrate state-of-the-art performance for pixel level classification of objects. Here we present a novel deep learning architecture, ResUNet-a, that combines ideas from various state-of-the-art modules used in computer vision for semantic segmentation tasks. We analyse the performance of several flavours of the Generalized Dice loss for semantic segmentation, and we introduce a novel variant loss function for semantic segmentation of objects that has better convergence properties and behaves well even under the presence of highly imbalanced classes. The performance of our modelling framework is evaluated on the ISPRS 2D Potsdam dataset. Results show state-of-the-art performance with an average F1 score of 92.1\% over all classes for our best model. …

Limited-memory BFGS (L-BFGS)
Limited-memory BFGS (L-BFGS or LM-BFGS) is an optimization algorithm in the family of quasi-Newton methods that approximates the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm using a limited amount of computer memory. It is a popular algorithm for parameter estimation in machine learning. …

OpenHowNet
In this paper, we present an open sememe-based lexical knowledge base OpenHowNet. Based on well-known HowNet, OpenHowNet comprises three components: core data which is composed of more than 100 thousand senses annotated with sememes, OpenHowNet Web which gives a brief introduction to OpenHowNet as well as provides online exhibition of OpenHowNet information, and OpenHowNet API which includes several useful APIs such as accessing OpenHowNet core data and drawing sememe tree structures of senses. In the main text, we first give some backgrounds including definition of sememe and details of HowNet. And then we introduce some previous HowNet and sememe-based research works. Last but not least, we detail the constituents of OpenHowNet and their basic features and functionalities. Additionally, we briefly make a summary and list some future works. …

Physics Enhanced Artificial Intelligence (PEAI)
We propose that intelligently combining models from the domains of Artificial Intelligence or Machine Learning with Physical and Expert models will yield a more ‘trustworthy’ model than any one model from a single domain, given a complex and narrow enough problem. Based on mean-variance portfolio theory and bias-variance trade-off analysis, we prove combining models from various domains produces a model that has lower risk, increasing user trust. We call such combined models – physics enhanced artificial intelligence (PEAI), and suggest use cases for PEAI. …

REINFORCE-based Genetic Algorithm Learning (REGAL)
We present a deep reinforcement learning approach to optimizing the execution cost of computation graphs in a static compiler. The key idea is to combine a neural network policy with a genetic algorithm, the Biased Random-Key Genetic Algorithm (BRKGA). The policy is trained to predict, given an input graph to be optimized, the node-level probability distributions for sampling mutations and crossovers in BRKGA. Our approach, ‘REINFORCE-based Genetic Algorithm Learning’ (REGAL), uses the policy’s ability to transfer to new graphs to significantly improve the solution quality of the genetic algorithm for the same objective evaluation budget. As a concrete application, we show results for minimizing peak memory in TensorFlow graphs by jointly optimizing device placement and scheduling. REGAL achieves on average 3.56% lower peak memory than BRKGA on previously unseen graphs, outperforming all the algorithms we compare to, and giving 4.4x bigger improvement than the next best algorithm. We also evaluate REGAL on a production compiler team’s performance benchmark of XLA graphs and achieve on average 3.74% lower peak memory than BRKGA, again outperforming all others. Our approach and analysis is made possible by collecting a dataset of 372 unique real-world TensorFlow graphs, more than an order of magnitude more data than previous work. …

Probabilistic PARAFAC2
The PARAFAC2 is a multimodal factor analysis model suitable for analyzing multi-way data when one of the modes has incomparable observation units, for example because of differences in signal sampling or batch sizes. A fully probabilistic treatment of the PARAFAC2 is desirable in order to improve robustness to noise and provide a well founded principle for determining the number of factors, but challenging because the factor loadings are constrained to be orthogonal. We develop two probabilistic formulations of the PARAFAC2 along with variational procedures for inference: In the one approach, the mean values of the factor loadings are orthogonal leading to closed form variational updates, and in the other, the factor loadings themselves are orthogonal using a matrix Von Mises-Fisher distribution. We contrast our probabilistic formulation to the conventional direct fitting algorithm based on maximum likelihood. On simulated data and real fluorescence spectroscopy and gas chromatography-mass spectrometry data, we compare our approach to the conventional PARAFAC2 model estimation and find that the probabilistic formulation is more robust to noise and model order misspecification. The probabilistic PARAFAC2 thus forms a promising framework for modeling multi-way data accounting for uncertainty. …

Noisy Multi-Label Semi-Supervised Dimensionality Reduction (NMLSDR)
Noisy labeled data represent a rich source of information that often are easily accessible and cheap to obtain, but label noise might also have many negative consequences if not accounted for. How to fully utilize noisy labels has been studied extensively within the framework of standard supervised machine learning over a period of several decades. However, very little research has been conducted on solving the challenge posed by noisy labels in non-standard settings. This includes situations where only a fraction of the samples are labeled (semi-supervised) and each high-dimensional sample is associated with multiple labels. In this work, we present a novel semi-supervised and multi-label dimensionality reduction method that effectively utilizes information from both noisy multi-labels and unlabeled data. With the proposed Noisy multi-label semi-supervised dimensionality reduction (NMLSDR) method, the noisy multi-labels are denoised and unlabeled data are labeled simultaneously via a specially designed label propagation algorithm. NMLSDR then learns a projection matrix for reducing the dimensionality by maximizing the dependence between the enlarged and denoised multi-label space and the features in the projected space. Extensive experiments on synthetic data, benchmark datasets, as well as a real-world case study, demonstrate the effectiveness of the proposed algorithm and show that it outperforms state-of-the-art multi-label feature extraction algorithms. …

Structure Tree-LSTM
We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements like words and sentences into blocks of increasing complexity. Our Structure Tree-LSTM implements a hierarchical attention mechanism over individual components and combinations thereof. We thus emphasize the usefulness of Tree-LSTMs for texts larger than a sentence. We show that structure-aware encoders can be used to improve the performance of document classification. We demonstrate that our method is resilient to changes to the basic building blocks, as it performs well with both sentence and word embeddings. The Structure Tree-LSTM outperforms all the baselines on two datasets when structural clues like sections are available, but also in the presence of mere paragraphs. On a third dataset from the medical domain, our model achieves competitive performance with the state of the art. This result shows the Structure Tree-LSTM can leverage dependency relations other than text structure, such as a set of reports on the same patient. …

GETNET
Change detection (CD) is an important application of remote sensing, which provides timely change information about large-scale Earth surface. With the emergence of hyperspectral imagery, CD technology has been greatly promoted, as hyperspectral data with the highspectral resolution are capable of detecting finer changes than using the traditional multispectral imagery. Nevertheless, the high dimension of hyperspectral data makes it difficult to implement traditional CD algorithms. Besides, endmember abundance information at subpixel level is often not fully utilized. In order to better handle high dimension problem and explore abundance information, this paper presents a General End-to-end Two-dimensional CNN (GETNET) framework for hyperspectral image change detection (HSI-CD). The main contributions of this work are threefold: 1) Mixed-affinity matrix that integrates subpixel representation is introduced to mine more cross-channel gradient features and fuse multi-source information; 2) 2-D CNN is designed to learn the discriminative features effectively from multi-source data at a higher level and enhance the generalization ability of the proposed CD algorithm; 3) A new HSI-CD data set is designed for the objective comparison of different methods. Experimental results on real hyperspectral data sets demonstrate the proposed method outperforms most of the state-of-the-arts. …

Intervention Analysis (IA)
Intervention analysis is the application of modeling procedures for incorporating the effects of exogenous forces or interventions in time series analysis. These interventions, like policy changes, strikes, floods, and price changes, cause unusual changes in time series, resulting in unexpected, extraordinary observations known as outliers. Specifically, four types of outliers resulting from interventions, additive outliers (AO), innovational outliers (IO), temporary changes (TC), and level shifts (LS), have generated a lot of interest in literature. They pose nonstationarity challenges, which cannot be represented by the usual Box and Jenkins (1976) autoregressive integrated moving average (ARIMA) models alone. The most popular modeling procedures are those where ‘intervention’ detection and estimation is paramount. Box and Tiao (1975) pioneered this type of analysis in their quest to solve the Los Angeles pollution problem. Important extensions and contributions have been made by Chan … …

Policy Optimization with Model-based Explorations (POME)
Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high sample complexity. On the other hand, model-based reinforcement learning methods that learn the transition dynamics are more sample efficient, but they often suffer from the bias of the transition estimation. How to make use of both model-based and model-free learning is a central problem in reinforcement learning. In this paper, we present a new technique to address the trade-off between exploration and exploitation, which regards the difference between model-free and model-based estimations as a measure of exploration value. We apply this new technique to the PPO algorithm and arrive at a new policy optimization method, named Policy Optimization with Model-based Explorations (POME). POME uses two components to predict the actions’ target values: a model-free one estimated by Monte-Carlo sampling and a model-based one which learns a transition model and predicts the value of the next state. POME adds the error of these two target estimations as the additional exploration value for each state-action pair, i.e, encourages the algorithm to explore the states with larger target errors which are hard to estimate. We compare POME with PPO on Atari 2600 games, and it shows that POME outperforms PPO on 33 games out of 49 games. …

Aspect Based Sentiment Analysis (ABSA)
Targeted sentiment analysis (TSA), also known as aspect based sentiment analysis (ABSA), aims at detecting fine-grained sentiment polarity towards targets in a given opinion document. Due to the lack of labeled datasets and effective technology, TSA had been intractable for many years. The newly released datasets and the rapid development of deep learning technologies are key enablers for the recent significant progress made in this area. However, the TSA tasks have been defined in various ways with different understandings towards basic concepts like `target’ and `aspect’. In this paper, we categorize the different tasks and highlight the differences in the available datasets and their specific tasks. We then further discuss the challenges related to data collection and data annotation which are overlooked in many previous studies. …

torchbearer
We introduce torchbearer, a model fitting library for pytorch aimed at researchers working on deep learning or differentiable programming. The torchbearer library provides a high level metric and callback API that can be used for a wide range of applications. We also include a series of built in callbacks that can be used for: model persistence, learning rate decay, logging, data visualization and more. The extensive documentation includes an example library for deep learning and dynamic programming problems and can be found at http://torchbearer.readthedocs.io. The code is licensed under the MIT License and available at https://…/torchbearer. …

Model-Based Pricing (MBP)
Data analytics using machine learning (ML) has become ubiquitous in science, business intelligence, journalism and many other domains. While a lot of work focuses on reducing the training cost, inference runtime and storage cost of ML models, little work studies how to reduce the cost of data acquisition, which potentially leads to a loss of sellers’ revenue and buyers’ affordability and efficiency. In this paper, we propose a model-based pricing (MBP) framework, which instead of pricing the data, directly prices ML model instances. We first formally describe the desired properties of the MBP framework, with a focus on avoiding arbitrage. Next, we show a concrete realization of the MBP framework via a noise injection approach, which provably satisfies the desired formal properties. Based on the proposed framework, we then provide algorithmic solutions on how the seller can assign prices to models under different market scenarios (such as to maximize revenue). Finally, we conduct extensive experiments, which validate that the MBP framework can provide high revenue to the seller, high affordability to the buyer, and also operate on low runtime cost. …

Hyperdimensional Computing
Hyperdimensional computing (HDC) is an emerging computing framework that takes inspiration from attributes of neuronal circuits such as hyperdimensionality, fully distributed holographic representation, and (pseudo)randomness. When employed for machine learning tasks such as learning and classification, HDC involves manipulation and comparison of large patterns within memory. Moreover, a key attribute of HDC is its robustness to the imperfections associated with the computational substrates on which it is implemented. It is therefore particularly amenable to emerging non-von Neumann paradigms such as in-memory computing, where the physical attributes of nanoscale memristive devices are exploited to perform computation in place. …

Weighted Multisource Tradaboost
In this paper we propose an improved method for transfer learning that takes into account the balance between target and source data. This method builds on the state-of-the-art Multisource Tradaboost, but weighs the importance of each datapoint taking into account the amount of target and source data available. A comparative study is then presented exposing the performance of four transfer learning methods as well as the proposed Weighted Multisource Tradaboost. The experimental results show that the proposed method is able to outperform the base method as the number of target samples increase. These results are promising in the sense that source-target ratio weighing may be a path to improve current methods of transfer learning. However, against the asymptotic conjecture, all transfer learning methods tested in this work get outperformed by a no-transfer SVM for large number on target samples. …

Pachinkogram
Conditional Probabilities Visualisation …

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. …

Conditional Gradient Augmented Lagrangian (CGAL)
We propose a new conditional gradient (CG) type method that processes the augmented Lagrangian (AL) function for smooth minimization problems with linear inclusion constraints over a compact domain. The proposed method (CGAL: conditional gradient augmented Lagrangian) maintains favorable properties of the classical conditional gradient method, including cheap linear minimization oracle calls as well as low-dimensional updates, while being still applicable to key semidefinite programming problems where the existing conditional gradient methods do not apply or are too slow. Under the strong duality assumption, we prove that the new method converges with $\tilde{\mathcal{O}}(1/\sqrt{k})$ rate both in the primal objective residual and feasibility gap. We then provide step-size rules that significantly enhance the empirical convergence while retaining the rates. Our numerical results with semidefinite programming examples indicate the algorithm exhibits ${\mathcal{O}}(1/{k})$ and even linear rates in special cases in practice. …

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>. …

Architecture Compression
In this paper we propose a novel approach to model compression termed Architecture Compression. Instead of operating on the weight or filter space of the network like classical model compression methods, our approach operates on the architecture space. A 1-D CNN encoder-decoder is trained to learn a mapping from discrete architecture space to a continuous embedding and back. Additionally, this embedding is jointly trained to regress accuracy and parameter count in order to incorporate information about the architecture’s effectiveness on the dataset. During the compression phase, we first encode the network and then perform gradient descent in continuous space to optimize a compression objective function that maximizes accuracy and minimizes parameter count. The final continuous feature is then mapped to a discrete architecture using the decoder. We demonstrate the merits of this approach on visual recognition tasks such as CIFAR-10, CIFAR-100, Fashion-MNIST and SVHN and achieve a greater than 20x compression on CIFAR-10. …

Robust Continuous Co-Clustering (ROCCO)
Clustering consists of grouping together samples giving their similar properties. The problem of modeling simultaneously groups of samples and features is known as Co-Clustering. This paper introduces ROCCO – a Robust Continuous Co-Clustering algorithm. ROCCO is a scalable, hyperparameter-free, easy and ready to use algorithm to address Co-Clustering problems in practice over massive cross-domain datasets. It operates by learning a graph-based two-sided representation of the input matrix. The underlying proposed optimization problem is non-convex, which assures a flexible pool of solutions. Moreover, we prove that it can be solved with a near linear time complexity on the input size. An exhaustive large-scale experimental testbed conducted with both synthetic and real-world datasets demonstrates ROCCO’s properties in practice: (i) State-of-the-art performance in cross-domain real-world problems including Biomedicine and Text Mining; (ii) very low sensitivity to hyperparameter settings; (iii) robustness to noise and (iv) a linear empirical scalability in practice. These results highlight ROCCO as a powerful general-purpose co-clustering algorithm for cross-domain practitioners, regardless of their technical background. …

DGD+LOCAL
We study the convergence of a variant of distributed gradient descent (DGD) on a distributed low-rank matrix approximation problem wherein some optimization variables are used for consensus (as in classical DGD) and some optimization variables appear only locally at a single node in the network. We term the resulting algorithm DGD+LOCAL. Using algorithmic connections to gradient descent and geometric connections to the well-behaved landscape of the centralized low-rank matrix approximation problem, we identify sufficient conditions where DGD+LOCAL is guaranteed to converge with exact consensus to a global minimizer of the original centralized problem. For the distributed low-rank matrix approximation problem, these guarantees are stronger—in terms of consensus and optimality—than what appear in the literature for classical DGD and more general problems. …

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. …

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. …