Deep Reinforcement Learning based Recommendation (DRR)
Recommendation is crucial in both academia and industry, and various techniques are proposed such as content-based collaborative filtering, matrix factorization, logistic regression, factorization machines, neural networks and multi-armed bandits. However, most of the previous studies suffer from two limitations: (1) considering the recommendation as a static procedure and ignoring the dynamic interactive nature between users and the recommender systems, (2) focusing on the immediate feedback of recommended items and neglecting the long-term rewards. To address the two limitations, in this paper we propose a novel recommendation framework based on deep reinforcement learning, called DRR. The DRR framework treats recommendation as a sequential decision making procedure and adopts an ‘Actor-Critic’ reinforcement learning scheme to model the interactions between the users and recommender systems, which can consider both the dynamic adaptation and long-term rewards. Furthermore, a state representation module is incorporated into DRR, which can explicitly capture the interactions between items and users. Three instantiation structures are developed. Extensive experiments on four real-world datasets are conducted under both the offline and online evaluation settings. The experimental results demonstrate the proposed DRR method indeed outperforms the state-of-the-art competitors. …

Deep Learning
Deep learning is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations. Deep learning is part of a broader family of machine learning methods based on learning representations. An observation (e.g., an image) can be represented in many ways (e.g., a vector of pixels), but some representations make it easier to learn tasks of interest (e.g., is this the image of a human face?) from examples, and research in this area attempts to define what makes better representations and how to create models to learn these representations. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, and deep belief networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, and music/audio signal recognition where they have been shown to produce state-of-the-art results on various tasks. …

Centralized Coordinate Learning (CCL)
Owe to the rapid development of deep neural network (DNN) techniques and the emergence of large scale face databases, face recognition has achieved a great success in recent years. During the training process of DNN, the face features and classification vectors to be learned will interact with each other, while the distribution of face features will largely affect the convergence status of network and the face similarity computing in test stage. In this work, we formulate jointly the learning of face features and classification vectors, and propose a simple yet effective centralized coordinate learning (CCL) method, which enforces the features to be dispersedly spanned in the coordinate space while ensuring the classification vectors to lie on a hypersphere. An adaptive angular margin is further proposed to enhance the discrimination capability of face features. Extensive experiments are conducted on six face benchmarks, including those have large age gap and hard negative samples. Trained only on the small-scale CASIA Webface dataset with 460K face images from about 10K subjects, our CCL model demonstrates high effectiveness and generality, showing consistently competitive performance across all the six benchmark databases. …

Fast-Node2Vec
Node2Vec is a state-of-the-art general-purpose feature learning method for network analysis. However, current solutions cannot run Node2Vec on large-scale graphs with billions of vertices and edges, which are common in real-world applications. The existing distributed Node2Vec on Spark incurs significant space and time overhead. It runs out of memory even for mid-sized graphs with millions of vertices. Moreover, it considers at most 30 edges for every vertex in generating random walks, causing poor result quality. In this paper, we propose Fast-Node2Vec, a family of efficient Node2Vec random walk algorithms on a Pregel-like graph computation framework. Fast-Node2Vec computes transition probabilities during random walks to reduce memory space consumption and computation overhead for large-scale graphs. The Pregel-like scheme avoids space and time overhead of Spark’s read-only RDD structures and shuffle operations. Moreover, we propose a number of optimization techniques to further reduce the computation overhead for popular vertices with large degrees. Empirical evaluation show that Fast-Node2Vec is capable of computing Node2Vec on graphs with billions of vertices and edges on a mid-sized machine cluster. Compared to Spark-Node2Vec, Fast-Node2Vec achieves 7.7–122x speedups. …

Graph Convolutional Recurrent Neural Network (GCRNN)
Graph processes model a number of important problems such as identifying the epicenter of an earthquake or predicting weather. In this paper, we propose a Graph Convolutional Recurrent Neural Network (GCRNN) architecture specifically tailored to deal with these problems. GCRNNs use convolutional filter banks to keep the number of trainable parameters independent of the size of the graph and of the time sequences considered. We also put forward Gated GCRNNs, a time-gated variation of GCRNNs akin to LSTMs. When compared with GNNs and another graph recurrent architecture in experiments using both synthetic and real-word data, GCRNNs significantly improve performance while using considerably less parameters. …

Retecs
Testing in Continuous Integration (CI) involves test case prioritization, selection, and execution at each cycle. Selecting the most promising test cases to detect bugs is hard if there are uncertainties on the impact of committed code changes or, if traceability links between code and tests are not available. This paper introduces Retecs, a new method for automatically learning test case selection and prioritization in CI with the goal to minimize the round-trip time between code commits and developer feedback on failed test cases. The Retecs method uses reinforcement learning to select and prioritize test cases according to their duration, previous last execution and failure history. In a constantly changing environment, where new test cases are created and obsolete test cases are deleted, the Retecs method learns to prioritize error-prone test cases higher under guidance of a reward function and by observing previous CI cycles. By applying Retecs on data extracted from three industrial case studies, we show for the first time that reinforcement learning enables fruitful automatic adaptive test case selection and prioritization in CI and regression testing. …

Wisdom of Crowds (WOC)
The wisdom of the crowd is the collective opinion of a group of individuals rather than that of a single expert. A large group’s aggregated answers to questions involving quantity estimation, general world knowledge, and spatial reasoning has generally been found to be as good as, and often better than, the answer given by any of the individuals within the group. An explanation for this phenomenon is that there is idiosyncratic noise associated with each individual judgment, and taking the average over a large number of responses will go some way toward canceling the effect of this noise.[1] This process, while not new to the Information Age, has been pushed into the mainstream spotlight by social information sites such as Wikipedia, Yahoo! Answers, Quora, and other web resources that rely on human opinion.[2] Trial by jury can be understood as wisdom of the crowd, especially when compared to the alternative, trial by a judge, the single expert. In politics, sometimes sortition is held as an example of what wisdom of the crowd would look like. Decision-making would happen by a diverse group instead of by a fairly homogenous political group or party. Research within cognitive science has sought to model the relationship between wisdom of the crowd effects and individual cognition.
WoCE: a framework for clustering ensemble by exploiting the wisdom of Crowds theory …

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. …

Q-Learning Sine-Cosine Algorithm (QLSCA)
The sine-cosine algorithm (SCA) is a new population-based meta-heuristic algorithm. In addition to exploiting sine and cosine functions to perform local and global searches (hence the name sine-cosine), the SCA introduces several random and adaptive parameters to facilitate the search process. Although it shows promising results, the search process of the SCA is vulnerable to local minima/maxima due to the adoption of a fixed switch probability and the bounded magnitude of the sine and cosine functions (from -1 to 1). In this paper, we propose a new hybrid Q-learning sine-cosine- based strategy, called the Q-learning sine-cosine algorithm (QLSCA). Within the QLSCA, we eliminate the switching probability. Instead, we rely on the Q-learning algorithm (based on the penalty and reward mechanism) to dynamically identify the best operation during runtime. Additionally, we integrate two new operations (L\’evy flight motion and crossover) into the QLSCA to facilitate jumping out of local minima/maxima and enhance the solution diversity. To assess its performance, we adopt the QLSCA for the combinatorial test suite minimization problem. Experimental results reveal that the QLSCA is statistically superior with regard to test suite size reduction compared to recent state-of-the-art strategies, including the original SCA, the particle swarm test generator (PSTG), adaptive particle swarm optimization (APSO) and the cuckoo search strategy (CS) at the 95% confidence level. However, concerning the comparison with discrete particle swarm optimization (DPSO), there is no significant difference in performance at the 95% confidence level. On a positive note, the QLSCA statistically outperforms the DPSO in certain configurations at the 90% confidence level. …

Cyber-Physical System (CPS)
A cyber-physical (also styled cyberphysical) system (CPS) is a mechanism that is controlled or monitored by computer-based algorithms, tightly integrated with the Internet and its users. In cyber-physical systems, physical and software components are deeply intertwined, each operating on different spatial and temporal scales, exhibiting multiple and distinct behavioral modalities, and interacting with each other in a lot of ways that change with context. Examples of CPS include smart grid, autonomous automobile systems, medical monitoring, process control systems, robotics systems, and automatic pilot avionics. CPS involves transdisciplinary approaches, merging theory of cybernetics, mechatronics, design and process science. The process control is often referred to as embedded systems. In embedded systems, the emphasis tends to be more on the computational elements, and less on an intense link between the computational and physical elements. CPS is also similar to the Internet of Things (IoT), sharing the same basic architecture; nevertheless, CPS presents a higher combination and coordination between physical and computational elements. Precursors of cyber-physical systems can be found in areas as diverse as aerospace, automotive, chemical processes, civil infrastructure, energy, healthcare, manufacturing, transportation, entertainment, and consumer appliances.
Cyber-Physical Systems, a new formal paradigm to model redundancy and resiliency …

iPrescribe
In this paper, we present iPrescribe, a scalable low-latency architecture for recommending ‘next-best-offers’ in an online setting. The paper presents the design of iPrescribe and compares its performance for implementations using different real-time streaming technology stacks. iPrescribe uses an ensemble of deep learning and machine learning algorithms for prediction. We describe the scalable real-time streaming technology stack and optimized machine-learning implementations to achieve a 90th percentile recommendation latency of 38 milliseconds. Optimizations include a novel mechanism to deploy recurrent Long Short Term Memory (LSTM) deep learning networks efficiently. …

Concept Mask
Existing works on semantic segmentation typically consider a small number of labels, ranging from tens to a few hundreds. With a large number of labels, training and evaluation of such task become extremely challenging due to correlation between labels and lack of datasets with complete annotations. We formulate semantic segmentation as a problem of image segmentation given a semantic concept, and propose a novel system which can potentially handle an unlimited number of concepts, including objects, parts, stuff, and attributes. We achieve this using a weakly and semi-supervised framework leveraging multiple datasets with different levels of supervision. We first train a deep neural network on a 6M stock image dataset with only image-level labels to learn visual-semantic embedding on 18K concepts. Then, we refine and extend the embedding network to predict an attention map, using a curated dataset with bounding box annotations on 750 concepts. Finally, we train an attention-driven class agnostic segmentation network using an 80-category fully annotated dataset. We perform extensive experiments to validate that the proposed system performs competitively to the state of the art on fully supervised concepts, and is capable of producing accurate segmentations for weakly learned and unseen concepts. …

Semiotics
Semiotics (also called semiotic studies) is the study of sign process (semiosis), which is any form of activity, conduct, or any process that involves signs, including the production of meaning. A sign is anything that communicates a meaning, that is not the sign itself, to the interpreter of the sign. The meaning can be intentional such as a word uttered with a specific meaning, or unintentional, such as a symptom being a sign of a particular medical condition. Signs can communicate through any of the senses, visual, auditory, tactile, olfactory, or taste. The semiotic tradition explores the study of signs and symbols as a significant part of communications. Unlike linguistics, semiotics also studies non-linguistic sign systems. Semiotics includes the study of signs and sign processes, indication, designation, likeness, analogy, allegory, metonymy, metaphor, symbolism, signification, and communication. Semiotics is frequently seen as having important anthropological and sociological dimensions; for example, the Italian semiotician and novelist Umberto Eco proposed that every cultural phenomenon may be studied as communication. Some semioticians focus on the logical dimensions of the science, however. They examine areas belonging also to the life sciences – such as how organisms make predictions about, and adapt to, their semiotic niche in the world (see semiosis). In general, semiotic theories take signs or sign systems as their object of study: the communication of information in living organisms is covered in biosemiotics (including zoosemiotics and phytosemiotics). Semiotics is not to be confused with the Saussurean tradition called semiology, which is a subset of semiotics. …

Complier Average Causal Effects (CACE)
Typically, studies analyze data based on treatment assignment rather than treatment received. This focus on assignment is called an intention-to-treat (ITT) analysis. In a policy environment, the ITT may make a lot of sense; we are answering this specific question: ‘What is the overall effect in the real world where the intervention is made available yet some people take advantage of it while others do not?’ Alternatively, researchers may be interested in different question: ‘What is the causal effect of actually receiving the treatment?’ Now, to answer the second question, there are numerous subtle issues that you need to wrestle with (again, go take the course). But, long story short, we need to (1) identify the folks in the intervention group who actually do what they have been encouraged to do (receive the intervention) but only because they were encouraged, and not because they would have received the intervention anyways had they not been randomized, and compare their outcomes with (2) the folks in the control group who did not seek out the intervention on their own initiative but would have received the intervention had they been encouraged. These two groups are considered to be compliers – they would always do what they are told in the context of the study. And the effect of the intervention that is based on outcomes from this type of patient is called the complier average causal effect (CACE). …

Augmented Inverse Probability Weighting (AIPWT)
In this paper, we discuss an estimator for average treatment effects (ATEs) known as the augmented inverse propensity weighted (AIPW) estimator. This estimator has attractive theoretical properties and only requires practitioners to do two things they are already comfortable with: (1) specify a binary regression model for the propensity score, and (2) specify a regression model for the outcome variable. Perhaps the most interesting property of this estimator is its so-called ‘‘double robustness.” Put simply, the estimator remains consistent for the ATE if either the propensity score model or the outcome regression is misspecified but the other is properly specified. After explaining the AIPW estimator, we conduct a Monte Carlo experiment that compares the finite sample performance of the AIPW estimator to three common competitors: a regression estimator, an inverse propensity weighted (IPW) estimator, and a propensity score matching estimator. The Monte Carlo results show that the AIPW estimator has comparable or lower mean square error than the competing estimators when the propensity score and outcome models are both properly specified and, when one of the models is misspecified, the AIPW estimator is superior.
‘Robust-squared’ Imputation Models Using BART …

FuzzerGym
Fuzzing is a commonly used technique designed to test software by automatically crafting program inputs. Currently, the most successful fuzzing algorithms emphasize simple, low-overhead strategies with the ability to efficiently monitor program state during execution. Through compile-time instrumentation, these approaches have access to numerous aspects of program state including coverage, data flow, and heterogeneous fault detection and classification. However, existing approaches utilize blind random mutation strategies when generating test inputs. We present a different approach that uses this state information to optimize mutation operators using reinforcement learning (RL). By integrating OpenAI Gym with libFuzzer we are able to simultaneously leverage advancements in reinforcement learning as well as fuzzing to achieve deeper coverage across several varied benchmarks. Our technique connects the rich, efficient program monitors provided by LLVM Santizers with a deep neural net to learn mutation selection strategies directly from the input data. The cross-language, asynchronous architecture we developed enables us to apply any OpenAI Gym compatible deep reinforcement learning algorithm to any fuzzing problem with minimal slowdown. …

No-Reference Image Quality Assessment (NR-IQA)
In this paper we investigate into the problem of image quality assessment (IQA) and enhancement via machine learning. This issue has long attracted a wide range of attention in computational intelligence and image processing communities, since, for many practical applications, e.g. object detection and recognition, raw images are usually needed to be appropriately enhanced to raise the visual quality (e.g. visibility and contrast). In fact, proper enhancement can noticeably improve the quality of input images, even better than originally captured images which are generally thought to be of the best quality. In this work, we present two most important contributions. The first contribution is to develop a new no-reference image quality assessment (NR-IQA) model. Given an image, our quality measure first extracts 17 features through analysis of contrast, sharpness, brightness and more, and then yields a measre of visual quality using a regression module, which is learned with big-data training samples that are much bigger than the size of relevant image datasets. Results of experiments on nine datasets validate the superiority and efficiency of our blind metric compared with typical state-of-the-art full-, reduced- and no-reference IQA methods. The second contribution is that a robust image enhancement framework is established based on quality optimization. For an input image, by the guidance of the proposed NR-IQA measure, we conduct histogram modification to successively rectify image brightness and contrast to a proper level. Thorough tests demonstrate that our framework can well enhance natural images, low-contrast images, low-light images and dehazed images. The source code will be released at https://…/publications. …

Contingency Training
When applied to high-dimensional datasets, feature selection algorithms might still leave dozens of irrelevant variables in the dataset. Therefore, even after feature selection has been applied, classifiers must be prepared to the presence of irrelevant variables. This paper investigates a new training method called Contingency Training which increases the accuracy as well as the robustness against irrelevant attributes. Contingency training is classifier independent. By subsampling and removing information from each sample, it creates a set of constraints. These constraints aid the method to automatically find proper importance weights of the dataset’s features. Experiments are conducted with the contingency training applied to neural networks over traditional datasets as well as datasets with additional irrelevant variables. For all of the tests, contingency training surpassed the unmodified training on datasets with irrelevant variables and even outperformed slightly when only a few or no irrelevant variables were present. …

Deductron
The current paper is a study in Recurrent Neural Networks (RNN), motivated by the lack of examples simple enough so that they can be thoroughly understood theoretically, but complex enough to be realistic. We constructed an example of structured data, motivated by problems from image-to-text conversion (OCR), which requires long-term memory to decode. Our data is a simple writing system, encoding characters ‘X’ and ‘O’ as their upper halves, which is possible due to symmetry of the two characters. The characters can be connected, as in some languages using cursive, such as Arabic (abjad). The string ‘XOOXXO’ may be encoded as ‘${\vee}{\wedge}\kern-1.5pt{\wedge}{\vee}\kern-1.5pt{\vee}{\wedge}$’. It follows that we may need to know arbitrarily long past to decode a current character, thus requiring long-term memory. Subsequently we constructed an RNN capable of decoding sequences encoded in this manner. Rather than by training, we constructed our RNN ‘by inspection’, i.e. we guessed its weights. This involved a sequence of steps. We wrote a conventional program which decodes the sequences as the example above. Subsequently, we interpreted the program as a neural network (the only example of this kind known to us). Finally, we generalized this neural network to discover a new RNN architecture whose instance is our handcrafted RNN. It turns out to be a 3 layer network, where the middle layer is capable of performing simple logical inferences; thus the name ‘deductron’. It is demonstrated that it is possible to train our network by simulated annealing. Also, known variants of stochastic gradient descent (SGD) methods are shown to work. …

DBSCAN++
DBSCAN is a classical density-based clustering procedure which has had tremendous practical relevance. However, it implicitly needs to compute the empirical density for each sample point, leading to a quadratic worst-case time complexity, which may be too slow on large datasets. We propose DBSCAN++, a simple modification of DBSCAN which only requires computing the densities for a subset of the points. We show empirically that, compared to traditional DBSCAN, DBSCAN++ can provide not only competitive performance but also added robustness in the bandwidth hyperparameter while taking a fraction of the runtime. We also present statistical consistency guarantees showing the trade-off between computational cost and estimation rates. Surprisingly, up to a certain point, we can enjoy the same estimation rates while lowering computational cost, showing that DBSCAN++ is a sub-quadratic algorithm that attains minimax optimal rates for level-set estimation, a quality that may be of independent interest. …

Quantile Option Architecture (QUOTA)
In this paper, we propose the Quantile Option Architecture (QUOTA) for exploration based on recent advances in distributional reinforcement learning (RL). In QUOTA, decision making is based on quantiles of a value distribution, not only the mean. QUOTA provides a new dimension for exploration via making use of both optimism and pessimism of a value distribution. We demonstrate the performance advantage of QUOTA in both challenging video games and physical robot simulators. …

Adversarial Multimedia Recommendation (AMR)
With the prevalence of multimedia content on the Web, developing recommender solutions that can effectively leverage the rich signal in multimedia data is in urgent need. Owing to the success of deep neural networks in representation learning, recent advance on multimedia recommendation has largely focused on exploring deep learning methods to improve the recommendation accuracy. To date, however, there has been little effort to investigate the robustness of multimedia representation and its impact on the performance of multimedia recommendation. In this paper, we shed light on the robustness of multimedia recommender system. Using the state-of-the-art recommendation framework and deep image features, we demonstrate that the overall system is not robust, such that a small (but purposeful) perturbation on the input image will severely decrease the recommendation accuracy. This implies the possible weakness of multimedia recommender system in predicting user preference, and more importantly, the potential of improvement by enhancing its robustness. To this end, we propose a novel solution named Adversarial Multimedia Recommendation (AMR), which can lead to a more robust multimedia recommender model by using adversarial learning. The idea is to train the model to defend an adversary, which adds perturbations to the target image with the purpose of decreasing the model’s accuracy. We conduct experiments on two representative multimedia recommendation tasks, namely, image recommendation and visually-aware product recommendation. Extensive results verify the positive effect of adversarial learning and demonstrate the effectiveness of our AMR method. Source codes are available in https://…/AMR. …

Algebraic Subspace Clustering (ASC)
Algebraic Subspace Clustering (ASC) is a simple and elegant method based on polynomial fitting and differentiation for clustering noiseless data drawn from an arbitrary union of subspaces. In practice, however, ASC is limited to equi-dimensional subspaces because the estimation of the subspace dimension via algebraic methods is sensitive to noise. This paper proposes a new ASC algorithm that can handle noisy data drawn from subspaces of arbitrary dimensions. The key ideas are (1) to construct, at each point, a decreasing sequence of subspaces containing the subspace passing through that point; (2) to use the distances from any other point to each subspace in the sequence to construct a subspace clustering affinity, which is superior to alternative affinities both in theory and in practice. Experiments on the Hopkins 155 dataset demonstrate the superiority of the proposed method with respect to sparse and low rank subspace clustering methods. …

RedNet
Indoor semantic segmentation has always been a difficult task in computer vision. In this paper, we propose an RGB-D residual encoder-decoder architecture, named RedNet, for indoor RGB-D semantic segmentation. In RedNet, the residual module is applied to both the encoder and decoder as the basic building block, and the skip-connection is used to bypass the spatial feature between the encoder and decoder. In order to incorporate the depth information of the scene, a fusion structure is constructed, which makes inference on RGB image and depth image separately, and fuses their features over several layers. In order to efficiently optimize the network’s parameters, we propose a `pyramid supervision’ training scheme, which applies supervised learning over different layers in the decoder, to cope with the problem of gradients vanishing. Experiment results show that the proposed RedNet(ResNet-50) achieves a state-of-the-art mIoU accuracy of 47.8\% on the SUN RGB-D benchmark dataset. …

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. …

Batch Virtual Adversarial Training (BVAT)
We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not consider the smoothness of the model’s output distribution against local perturbations around the input. We propose two algorithms, sample-based BVAT and optimization-based BVAT, which are suitable to promote the smoothness of the model for graph-structured data by either finding virtual adversarial perturbations for a subset of nodes far from each other or generating virtual adversarial perturbations for all nodes with an optimization process. Extensive experiments on three citation network datasets Cora, Citeseer and Pubmed and a knowledge graph dataset Nell validate the effectiveness of the proposed method, which establishes state-of-the-art results in the semi-supervised node classification tasks. …

Markov Random Field (MRF)
In the domain of physics and probability, a Markov random field (often abbreviated as MRF), Markov network or undirected graphical model is a set of random variables having a Markov property described by an undirected graph. A Markov random field is similar to a Bayesian network in its representation of dependencies; the differences being that Bayesian networks are directed and acyclic, whereas Markov networks are undirected and may be cyclic. Thus, a Markov network can represent certain dependencies that a Bayesian network cannot (such as cyclic dependencies); on the other hand, it can’t represent certain dependencies that a Bayesian network can (such as induced dependencies). …

Bumping
Bumping is a simple algorithm that can help your classifier escape from a local minimum. The idea behind bumping is that we can break the symmetry of the problem (or escape the local minimum) by training a decision tree on random subsample. This is similar to bagging. The hope is that in the subsample there will be a preferred split so the tree can pick it. We fit several trees on different bootstrap) samples (sampling with replacement) and choose the one with the best performance on the full training set as the winner. The more rounds of bumping we do, the more likely we are to escape. It costs more CPU time as well though. …

Stochastic Model Predictive Control (SMPC)
Model predictive control (MPC) has demonstrated exceptional success for the high-performance control of complex systems. The conceptual simplicity of MPC as well as its ability to effectively cope with the complex dynamics of systems with multiple inputs and outputs, input and state/output constraints, and conflicting control objectives have made it an attractive multivariable constrained control approach. This article gives an overview of the main developments in the area of stochastic model predictive control (SMPC) in the past decade and provides the reader with an impression of the different SMPC algorithms and the key theoretical challenges in stochastic predictive control without undue mathematical complexity. The general formulation of a stochastic OCP is first presented, followed by an overview of SMPC approaches for linear and nonlinear systems. Suggestions of some avenues for future research in this rapidly evolving field concludes the article. …

Jazz
Jazz is a lightweight modular data processing framework, including a web server. It provides data persistence and computation capabilities accessible from R and Python and also through a REST API. …

Video Ladder Network (VLN)
We present the Video Ladder Network (VLN) for video prediction. VLN is a neural encoder-decoder model augmented by both recurrent and feedforward lateral connections at all layers. The model achieves competitive results on the Moving MNIST dataset while having very simple structure and providing fast inference. …

Low-Rank Principal Eigenmatrix Analysis
Sparse PCA is a widely used technique for high-dimensional data analysis. In this paper, we propose a new method called low-rank principal eigenmatrix analysis. Different from sparse PCA, the dominant eigenvectors are allowed to be dense but are assumed to have a low-rank structure when matricized appropriately. Such a structure arises naturally in several practical cases: Indeed the top eigenvector of a circulant matrix, when matricized appropriately is a rank-1 matrix. We propose a matricized rank-truncated power method that could be efficiently implemented and establish its computational and statistical properties. Extensive experiments on several synthetic data sets demonstrate the competitive empirical performance of our method. …

Inoculation by Fine-Tuning
Several datasets have recently been constructed to expose brittleness in models trained on existing benchmarks. While model performance on these challenge datasets is significantly lower compared to the original benchmark, it is unclear what particular weaknesses they reveal. For example, a challenge dataset may be difficult because it targets phenomena that current models cannot capture, or because it simply exploits blind spots in a model’s specific training set. We introduce inoculation by fine-tuning, a new analysis method for studying challenge datasets by exposing models (the metaphorical patient) to a small amount of data from the challenge dataset (a metaphorical pathogen) and assessing how well they can adapt. We apply our method to analyze the NLI ‘stress tests’ (Naik et al., 2018) and the Adversarial SQuAD dataset (Jia and Liang, 2017). We show that after slight exposure, some of these datasets are no longer challenging, while others remain difficult. Our results indicate that failures on challenge datasets may lead to very different conclusions about models, training datasets, and the challenge datasets themselves. …

Transformation Invariant Graph-Based Network (TIGraNet)
Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for image and video classification tasks. However, they have achieved only limited success in the classification of images that undergo geometric transformations. In this work we present a novel Transformation Invariant Graph-based Network (TIGraNet), which learns graph-based features that are inherently invariant to isometric transformations such as rotation and translation of input images. In particular, images are represented as signals on graphs, which permits to replace classical convolution and pooling layers in deep networks with graph spectral convolution and dynamic graph pooling layers that together contribute to invariance to isometric transformation. Our experiments show high performance on rotated and translated images from the test set compared to classical architectures that are very sensitive to transformations in the data. The inherent invariance properties of our framework provide key advantages, such as increased resiliency to data variability and sustained performance with limited training sets. Our code is available online. …

Video Transformer Network (VTN)
In this work we present a new efficient approach to Human Action Recognition called Video Transformer Network (VTN). It leverages the latest advances in Computer Vision and Natural Language Processing and applies them to video understanding. The proposed method allows us to create lightweight CNN models that achieve high accuracy and real-time speed using just an RGB mono camera and general purpose CPU. Furthermore, we explain how to improve accuracy by distilling from multiple models with different modalities into a single model. We conduct a comparison with state-of-the-art methods and show that our approach performs on par with most of them on famous Action Recognition datasets. We benchmark the inference time of the models using the modern inference framework and argue that our approach compares favorably with other methods in terms of speed/accuracy trade-off, running at 56 FPS on CPU. The models and the training code are available. …

Weakly-supervised Temporal Activity Localization (W-TALC)
Most activity localization methods in the literature suffer from the burden of frame-wise annotation requirement. Learning from weak labels may be a potential solution towards reducing such manual labeling effort. Recent years have witnessed a substantial influx of tagged videos on the Internet, which can serve as a rich source of weakly-supervised training data. Specifically, the correlations between videos with similar tags can be utilized to temporally localize the activities. Towards this goal, we present W-TALC, a Weakly-supervised Temporal Activity Localization and Classification framework using only video-level labels. The proposed network can be divided into two sub-networks, namely the Two-Stream based feature extractor network and a weakly-supervised module, which we learn by optimizing two complimentary loss functions. Qualitative and quantitative results on two challenging datasets – Thumos14 and ActivityNet1.2, demonstrate that the proposed method is able to detect activities at a fine granularity and achieve better performance than current state-of-the-art methods. …

RISE Analysis
Described in Bodily, Nyland, and Wiley (2017) <doi:10.19173/irrodl.v18i2.2952>. Automates the process of identifying learning materials that are not effectively supporting student learning in technology-mediated courses by synthesizing information about access to course content and performance on assessments.
The RISE (Resource Inspection, Selection, and Enhancement) Framework is a framework supporting the continuous improvement of open educational resources (OER). The framework is an automated process that identifies learning resources that should be evaluated and either eliminated or improved. This is particularly useful in OER contexts where the copyright permissions of resources allow for remixing, editing, and improving content. The RISE Framework presents a scatterplot with resource usage on the x-axis and grade on the assessments associated with that resource on the y-axis. This scatterplot is broken down into four different quadrants (the mean of each variable being the origin) to find resources that are candidates for improvement. Resources that reside deep within their respective quadrant (farthest from the origin) should be further analyzed for continuous course improvement. We present a case study applying our framework with an Introduction to Business course. Aggregate resource use data was collected from Google Analytics and aggregate assessment data was collected from an online assessment system. Using the RISE Framework, we successfully identified resources, time periods, and modules in the course that should be further evaluated for improvement. …

HyperFusion-Net
Salient object detection (SOD), which aims to find the most important region of interest and segment the relevant object/item in that area, is an important yet challenging vision task. This problem is inspired by the fact that human seems to perceive main scene elements with high priorities. Thus, accurate detection of salient objects in complex scenes is critical for human-computer interaction. In this paper, we present a novel feature learning framework for SOD, in which we cast the SOD as a pixel-wise classification problem. The proposed framework utilizes a densely hierarchical feature fusion network, named HyperFusion-Net, automatically predicts the most important area and segments the associated objects in an end-to-end manner. Specifically, inspired by the human perception system and image reflection separation, we first decompose input images into reflective image pairs by content-preserving transforms. Then, the complementary information of reflective image pairs is jointly extracted by an interweaved convolutional neural network (ICNN) and hierarchically combined with a hyper-dense fusion mechanism. Based on the fused multi-scale features, our method finally achieves a promising way of predicting SOD. As shown in our extensive experiments, the proposed method consistently outperforms other state-of-the-art methods on seven public datasets with a large margin. …

Ludwig
Ludwig is a toolbox that allows to train and test deep learning models without the need to write code. …

RedSync
Data parallelism has already become a dominant method to scale Deep Neural Network (DNN) training to multiple computation nodes. Considering that the synchronization of local model or gradient between iterations can be a bottleneck for large-scale distributed training, compressing communication traffic has gained widespread attention recently. Among several recent proposed compression algorithms, Residual Gradient Compression (RGC) is one of the most successful approaches—it can significantly compress the message size (0.1% of the original size) and still preserve accuracy. However, the literature on compressing deep networks focuses almost exclusively on finding good compression rate, while the efficiency of RGC in real implementation has been less investigated. In this paper, we explore the potential of application RGC method in the real distributed system. Targeting the widely adopted multi-GPU system, we proposed an RGC system design call RedSync, which includes a set of optimizations to reduce communication bandwidth while introducing limited overhead. We examine the performance of RedSync on two different multiple GPU platforms, including a supercomputer and a multi-card server. Our test cases include image classification and language modeling tasks on Cifar10, ImageNet, Penn Treebank and Wiki2 datasets. For DNNs featured with high communication to computation ratio, which have long been considered with poor scalability, RedSync shows significant performance improvement. …