January 25, 2020

3288 words 16 mins read

Paper Group ANR 1653

Explainable AI: Deep Reinforcement Learning Agents for Residential Demand Side Cost Savings in Smart Grids. Neural Machine Reading Comprehension: Methods and Trends. Sparse Coding of Shape Trajectories for Facial Expression and Action Recognition. QuPWM: Feature Extraction Method for MEG Epileptic Spike Detection. An Actor-Critic-Attention Mechanis …

Explainable AI: Deep Reinforcement Learning Agents for Residential Demand Side Cost Savings in Smart Grids


Title	Explainable AI: Deep Reinforcement Learning Agents for Residential Demand Side Cost Savings in Smart Grids
Authors	Hareesh Kumar, Priyanka Mary Mammen, Krithi Ramamritham
Abstract	Motivated by recent advancements in Deep Reinforcement Learning (RL), we have developed an RL agent to manage the operation of storage devices in a household and is designed to maximize demand-side cost savings. The proposed technique is data-driven, and the RL agent learns from scratch how to efficiently use the energy storage device given variable tariff structures. In most of the studies, the RL agent is considered as a black box, and how the agent has learned is often ignored. We explain the learning progression of the RL agent, and the strategies it follows based on the capacity of the storage device.
Tasks
Published	2019-10-19
URL	https://arxiv.org/abs/1910.08719v2
PDF	https://arxiv.org/pdf/1910.08719v2.pdf
PWC	https://paperswithcode.com/paper/explainable-ai-deep-reinforcement-learning
Repo
Framework

Neural Machine Reading Comprehension: Methods and Trends


Title	Neural Machine Reading Comprehension: Methods and Trends
Authors	Shanshan Liu, Xin Zhang, Sheng Zhang, Hui Wang, Weiming Zhang
Abstract	Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques over the past few years. Although research on MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this article. Specifically, we give a thorough review of this research field, covering different aspects including (1) typical MRC tasks: their definitions, differences, and representative datasets; (2) the general architecture of neural MRC: the main modules and prevalent approaches to each; and (3) new trends: some emerging areas in neural MRC as well as the corresponding challenges. Finally, considering what has been achieved so far, the survey also envisages what the future may hold by discussing the open issues left to be addressed.
Tasks	Machine Reading Comprehension, Reading Comprehension
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01118v5
PDF	https://arxiv.org/pdf/1907.01118v5.pdf
PWC	https://paperswithcode.com/paper/neural-machine-reading-comprehension-methods
Repo
Framework

Sparse Coding of Shape Trajectories for Facial Expression and Action Recognition


Title	Sparse Coding of Shape Trajectories for Facial Expression and Action Recognition
Authors	Amor Ben Tanfous, Hassen Drira, Boulbaba Ben Amor
Abstract	The detection and tracking of human landmarks in video streams has gained in reliability partly due to the availability of affordable RGB-D sensors. The analysis of such time-varying geometric data is playing an important role in the automatic human behavior understanding. However, suitable shape representations as well as their temporal evolution, termed trajectories, often lie to nonlinear manifolds. This puts an additional constraint (i.e., nonlinearity) in using conventional Machine Learning techniques. As a solution, this paper accommodates the well-known Sparse Coding and Dictionary Learning approach to study time-varying shapes on the Kendall shape spaces of 2D and 3D landmarks. We illustrate effective coding of 3D skeletal sequences for action recognition and 2D facial landmark sequences for macro- and micro-expression recognition. To overcome the inherent nonlinearity of the shape spaces, intrinsic and extrinsic solutions were explored. As main results, shape trajectories give rise to more discriminative time-series with suitable computational properties, including sparsity and vector space structure. Extensive experiments conducted on commonly-used datasets demonstrate the competitiveness of the proposed approaches with respect to state-of-the-art.
Tasks	Dictionary Learning, Time Series
Published	2019-08-08
URL	https://arxiv.org/abs/1908.03231v1
PDF	https://arxiv.org/pdf/1908.03231v1.pdf
PWC	https://paperswithcode.com/paper/sparse-coding-of-shape-trajectories-for
Repo
Framework

QuPWM: Feature Extraction Method for MEG Epileptic Spike Detection


Title	QuPWM: Feature Extraction Method for MEG Epileptic Spike Detection
Authors	Abderrazak Chahid, Fahad Albalawi, Turky Nayef Alotaiby, Majed Hamad Al-Hameed, Saleh Alshebeili, Taous-Meriem Laleg-Kirati
Abstract	Epilepsy is a neurological disorder classified as the second most serious neurological disease known to humanity, after stroke. Localization of the epileptogenic zone is an important step for epileptic patient treatment, which starts with epileptic spike detection. The common practice for spike detection of brain signals is via visual scanning of the recordings, which is a subjective and a very time-consuming task. Motivated by that, this paper focuses on using machine learning for automatic detection of epileptic spikes in magnetoencephalography (MEG) signals. First, we used the Position Weight Matrix (PWM) method combined with a uniform quantizer to generate useful features. Second, the extracted features are classified using a Support Vector Machine (SVM) for the purpose of epileptic spikes detection. The proposed technique shows great potential in improving the spike detection accuracy and reducing the feature vector size. Specifically, the proposed technique achieved average accuracy up to 98% in using 5-folds cross-validation applied to a balanced dataset of 3104 samples. These samples are extracted from 16 subjects where eight are healthy and eight are epileptic subjects using a sliding frame of size of 100 samples-points with a step-size of 2 sample-points
Tasks
Published	2019-07-03
URL	https://arxiv.org/abs/1907.02596v1
PDF	https://arxiv.org/pdf/1907.02596v1.pdf
PWC	https://paperswithcode.com/paper/qupwm-feature-extraction-method-for-meg
Repo
Framework

An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments


Title	An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments
Authors	Elaheh Barati, Xuewen Chen
Abstract	In reinforcement learning algorithms, leveraging multiple views of the environment can improve the learning of complicated policies. In multi-view environments, due to the fact that the views may frequently suffer from partial observability, their level of importance are often different. In this paper, we propose a deep reinforcement learning method and an attention mechanism in a multi-view environment. Each view can provide various representative information about the environment. Through our attention mechanism, our method generates a single feature representation of environment given its multiple views. It learns a policy to dynamically attend to each view based on its importance in the decision-making process. Through experiments, we show that our method outperforms its state-of-the-art baselines on TORCS racing car simulator and three other complex 3D environments with obstacles. We also provide experimental results to evaluate the performance of our method on noisy conditions and partial observation settings.
Tasks	Decision Making
Published	2019-07-19
URL	https://arxiv.org/abs/1907.09466v1
PDF	https://arxiv.org/pdf/1907.09466v1.pdf
PWC	https://paperswithcode.com/paper/an-actor-critic-attention-mechanism-for-deep
Repo
Framework

Reservoir Computing based on Quenched Chaos


Title	Reservoir Computing based on Quenched Chaos
Authors	Jaesung Choi, Pilwon Kim
Abstract	Reservoir computing(RC) is a brain-inspired computing framework that employs a transient dynamical system whose reaction to an input signal is transformed to a target output. One of the central problems in RC is to find a reliable reservoir with a large criticality, since computing performance of a reservoir is maximized near the phase transition. In this work, we propose a continuous reservoir that utilizes transient dynamics of coupled chaotic oscillators in a critical regime where sudden amplitude death occurs. This “explosive death” not only brings the system a large criticality which provides a variety of orbits for computing, but also stabilizes them which otherwise diverge soon in chaotic units. The proposed framework shows better results in tasks for signal reconstructions than RC based on explosive synchronization of regular phase oscillators. We also show that the information capacity of the reservoirs can be used as a predictive measure for computational capability of a reservoir at a critical point.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.01571v1
PDF	https://arxiv.org/pdf/1909.01571v1.pdf
PWC	https://paperswithcode.com/paper/reservoir-computing-based-on-quenched-chaos
Repo
Framework

ProSper – A Python Library for Probabilistic Sparse Coding with Non-Standard Priors and Superpositions


Title	ProSper – A Python Library for Probabilistic Sparse Coding with Non-Standard Priors and Superpositions
Authors	Georgios Exarchakis, Jörg Bornschein, Abdul-Saboor Sheikh, Zhenwen Dai, Marc Henniges, Jakob Drefs, Jörg Lücke
Abstract	ProSper is a python library containing probabilistic algorithms to learn dictionaries. Given a set of data points, the implemented algorithms seek to learn the elementary components that have generated the data. The library widens the scope of dictionary learning approaches beyond implementations of standard approaches such as ICA, NMF or standard L1 sparse coding. The implemented algorithms are especially well-suited in cases when data consist of components that combine non-linearly and/or for data requiring flexible prior distributions. Furthermore, the implemented algorithms go beyond standard approaches by inferring prior and noise parameters of the data, and they provide rich a-posteriori approximations for inference. The library is designed to be extendable and it currently includes: Binary Sparse Coding (BSC), Ternary Sparse Coding (TSC), Discrete Sparse Coding (DSC), Maximal Causes Analysis (MCA), Maximum Magnitude Causes Analysis (MMCA), and Gaussian Sparse Coding (GSC, a recent spike-and-slab sparse coding approach). The algorithms are scalable due to a combination of variational approximations and parallelization. Implementations of all algorithms allow for parallel execution on multiple CPUs and multiple machines for medium to large-scale applications. Typical large-scale runs of the algorithms can use hundreds of CPUs to learn hundreds of dictionary elements from data with tens of millions of floating-point numbers such that models with several hundred thousand parameters can be optimized. The library is designed to have minimal dependencies and to be easy to use. It targets users of dictionary learning algorithms and Machine Learning researchers.
Tasks	Dictionary Learning
Published	2019-08-01
URL	https://arxiv.org/abs/1908.06843v1
PDF	https://arxiv.org/pdf/1908.06843v1.pdf
PWC	https://paperswithcode.com/paper/prosper-a-python-library-for-probabilistic
Repo
Framework

Learnable Pooling in Graph Convolution Networks for Brain Surface Analysis


Title	Learnable Pooling in Graph Convolution Networks for Brain Surface Analysis
Authors	Karthik Gopinath, Christian Desrosiers, Herve Lombaert
Abstract	Brain surface analysis is essential to neuroscience, however, the complex geometry of the brain cortex hinders computational methods for this task. The difficulty arises from a discrepancy between 3D imaging data, which is represented in Euclidean space, and the non-Euclidean geometry of the highly-convoluted brain surface. Recent advances in machine learning have enabled the use of neural networks for non-Euclidean spaces. These facilitate the learning of surface data, yet pooling strategies often remain constrained to a single fixed-graph. This paper proposes a new learnable graph pooling method for processing multiple surface-valued data to output subject-based information. The proposed method innovates by learning an intrinsic aggregation of graph nodes based on graph spectral embedding. We illustrate the advantages of our approach with in-depth experiments on two large-scale benchmark datasets. The flexibility of the pooling strategy is evaluated on four different prediction tasks, namely, subject-sex classification, regression of cortical region sizes, classification of Alzheimer’s disease stages, and brain age regression. Our experiments demonstrate the superiority of our learnable pooling approach compared to other pooling techniques for graph convolution networks, with results improving the state-of-the-art in brain surface analysis.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10129v1
PDF	https://arxiv.org/pdf/1911.10129v1.pdf
PWC	https://paperswithcode.com/paper/learnable-pooling-in-graph-convolution
Repo
Framework

Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning


Title	Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
Authors	De-An Huang, Danfei Xu, Yuke Zhu, Animesh Garg, Silvio Savarese, Li Fei-Fei, Juan Carlos Niebles
Abstract	We address one-shot imitation learning, where the goal is to execute a previously unseen task based on a single demonstration. While there has been exciting progress in this direction, most of the approaches still require a few hundred tasks for meta-training, which limits the scalability of the approaches. Our main contribution is to formulate one-shot imitation learning as a symbolic planning problem along with the symbol grounding problem. This formulation disentangles the policy execution from the inter-task generalization and leads to better data efficiency. The key technical challenge is that the symbol grounding is prone to error with limited training data and leads to subsequent symbolic planning failures. We address this challenge by proposing a continuous relaxation of the discrete symbolic planner that directly plans on the probabilistic outputs of the symbol grounding model. Our continuous relaxation of the planner can still leverage the information contained in the probabilistic symbol grounding and significantly improve over the baseline planner for the one-shot imitation learning tasks without using large training data.
Tasks	Imitation Learning
Published	2019-08-16
URL	https://arxiv.org/abs/1908.06769v2
PDF	https://arxiv.org/pdf/1908.06769v2.pdf
PWC	https://paperswithcode.com/paper/continuous-relaxation-of-symbolic-planner-for
Repo
Framework

Sentence Compression via DC Programming Approach


Title	Sentence Compression via DC Programming Approach
Authors	Yi-Shuai Niu, Xi-Wei Hu, Yu You, Faouzi Mohamed Benammour, Hu Zhang
Abstract	Sentence compression is an important problem in natural language processing. In this paper, we firstly establish a new sentence compression model based on the probability model and the parse tree model. Our sentence compression model is equivalent to an integer linear program (ILP) which can both guarantee the syntax correctness of the compression and save the main meaning. We propose using a DC (Difference of convex) programming approach (DCA) for finding local optimal solution of our model. Combing DCA with a parallel-branch-and-bound framework, we can find global optimal solution. Numerical results demonstrate the good quality of our sentence compression model and the excellent performance of our proposed solution algorithm.
Tasks	Sentence Compression
Published	2019-02-13
URL	http://arxiv.org/abs/1902.07248v1
PDF	http://arxiv.org/pdf/1902.07248v1.pdf
PWC	https://paperswithcode.com/paper/sentence-compression-via-dc-programming
Repo
Framework

A Compact Representation of Histopathology Images using Digital Stain Separation & Frequency-Based Encoded Local Projections


Title	A Compact Representation of Histopathology Images using Digital Stain Separation & Frequency-Based Encoded Local Projections
Authors	Alison K. Cheeseman, Hamid Tizhoosh, Edward R. Vrscay
Abstract	In recent years, histopathology images have been increasingly used as a diagnostic tool in the medical field. The process of accurately diagnosing a biopsy sample requires significant expertise in the field, and as such can be time-consuming and is prone to uncertainty and error. With the advent of digital pathology, using image recognition systems to highlight problem areas or locate similar images can aid pathologists in making quick and accurate diagnoses. In this paper, we specifically consider the encoded local projections (ELP) algorithm, which has previously shown some success as a tool for classification and recognition of histopathology images. We build on the success of the ELP algorithm as a means for image classification and recognition by proposing a modified algorithm which captures the local frequency information of the image. The proposed algorithm estimates local frequencies by quantifying the changes in multiple projections in local windows of greyscale images. By doing so we remove the need to store the full projections, thus significantly reducing the histogram size, and decreasing computation time for image retrieval and classification tasks. Furthermore, we investigate the effectiveness of applying our method to histopathology images which have been digitally separated into their hematoxylin and eosin stain components. The proposed algorithm is tested on the publicly available invasive ductal carcinoma (IDC) data set. The histograms are used to train an SVM to classify the data. The experiments showed that the proposed method outperforms the original ELP algorithm in image retrieval tasks. On classification tasks, the results are found to be comparable to state-of-the-art deep learning methods and better than many handcrafted features from the literature.
Tasks	Image Classification, Image Retrieval
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11945v1
PDF	https://arxiv.org/pdf/1905.11945v1.pdf
PWC	https://paperswithcode.com/paper/a-compact-representation-of-histopathology
Repo
Framework

Landmark Map: An Extension of the Self-Organizing Map for a User-Intended Nonlinear Projection


Title	Landmark Map: An Extension of the Self-Organizing Map for a User-Intended Nonlinear Projection
Authors	Akinari Onishi
Abstract	The self-organizing map (SOM) is an unsupervised artificial neural network that is widely used in, e.g., data mining and visualization. Supervised and semi-supervised learning methods have been proposed for the SOM. However, their teacher labels do not describe the relationship between the data and the location of nodes. This study proposes a landmark map (LAMA), which is an extension of the SOM that utilizes several landmarks, e.g., pairs of nodes and data points. LAMA is designed to obtain a user-intended nonlinear projection to achieve, e.g., the landmark-oriented data visualization. To reveal the learning properties of LAMA, the Zoo dataset from the UCI Machine Learning Repository and an artificial formant dataset were analyzed. The analysis results of the Zoo dataset indicated that LAMA could provide a new data view such as the landmark-centered data visualization. Furthermore, the artificial formant data analysis revealed that LAMA successfully provided the intended nonlinear projection associating articular movement with vertical and horizontal movement of a computer cursor. Potential applications of LAMA include data mining, recommendation systems, and human-computer interaction.
Tasks	Recommendation Systems
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07124v1
PDF	https://arxiv.org/pdf/1908.07124v1.pdf
PWC	https://paperswithcode.com/paper/landmark-map-an-extension-of-the-self
Repo
Framework

DL-Droid: Deep learning based android malware detection using real devices


Title	DL-Droid: Deep learning based android malware detection using real devices
Authors	Mohammed K. Alzaylaee, Suleiman Y. Yerima, Sakir Sezer
Abstract	The Android operating system has been the most popular for smartphones and tablets since 2012. This popularity has led to a rapid raise of Android malware in recent years. The sophistication of Android malware obfuscation and detection avoidance methods have significantly improved, making many traditional malware detection methods obsolete. In this paper, we propose DL-Droid, a deep learning system to detect malicious Android applications through dynamic analysis using stateful input generation. Experiments performed with over 30,000 applications (benign and malware) on real devices are presented. Furthermore, experiments were also conducted to compare the detection performance and code coverage of the stateful input generation method with the commonly used stateless approach using the deep learning system. Our study reveals that DL-Droid can achieve up to 97.8% detection rate (with dynamic features only) and 99.6% detection rate (with dynamic + static features) respectively which outperforms traditional machine learning techniques. Furthermore, the results highlight the significance of enhanced input generation for dynamic analysis as DL-Droid with the state-based input generation is shown to outperform the existing state-of-the-art approaches.
Tasks	Android Malware Detection, Malware Detection
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10113v1
PDF	https://arxiv.org/pdf/1911.10113v1.pdf
PWC	https://paperswithcode.com/paper/dl-droid-deep-learning-based-android-malware
Repo
Framework

Which Tasks Should Be Learned Together in Multi-task Learning?


Title	Which Tasks Should Be Learned Together in Multi-task Learning?
Authors	Trevor Standley, Amir R. Zamir, Dawn Chen, Leonidas Guibas, Jitendra Malik, Silvio Savarese
Abstract	Many computer vision applications require solving multiple tasks in real-time. A neural network can be trained to solve multiple tasks simultaneously using `multi-task learning’. This saves computation at inference time as only a single network needs to be evaluated. Unfortunately, this often leads to inferior overall performance as task objectives compete, which consequently poses the question: which tasks should and should not be learned together in one network when employing multi-task learning? We systematically study task cooperation and competition and propose a framework for assigning tasks to a few neural networks such that cooperating tasks are computed by the same neural network, while competing tasks are computed by different networks. Our framework offers a time-accuracy trade-off and can produce better accuracy using less inference time than not only a single large multi-task neural network but also many single-task networks. \|
Tasks	Multi-Task Learning
Published	2019-05-18
URL	https://arxiv.org/abs/1905.07553v2
PDF	https://arxiv.org/pdf/1905.07553v2.pdf
PWC	https://paperswithcode.com/paper/which-tasks-should-be-learned-together-in
Repo
Framework

Self-Supervised Similarity Learning for Digital Pathology


Title	Self-Supervised Similarity Learning for Digital Pathology
Authors	Jacob Gildenblat, Eldad Klaiman
Abstract	Using features extracted from networks pretrained on ImageNet is a common practice in applications of deep learning for digital pathology. However it presents the downside of missing domain specific image information. In digital pathology, supervised training data is expensive and difficult to collect. We propose a self-supervised method for feature extraction by similarity learning on whole slide images (WSI) that is simple to implement and allows creation of robust and compact image descriptors. We train a siamese network, exploiting image spatial continuity and assuming spatially adjacent tiles in the image are more similar to each other than distant tiles. Our network outputs feature vectors of length 128, which allows dramatically lower memory storage and faster processing than networks pretrained on ImageNet. We apply the method on digital pathology WSIs from the Camelyon16 train set and assess and compare our method by measuring image retrieval of tumor tiles and descriptor pair distance ratio for distant/near tiles in the Camelyon16 test set. We show that our method yields better retrieval task results than existing ImageNet based and generic self-supervised feature extraction methods. To the best of our knowledge, this is also the first published method for self-supervised learning tailored for digital pathology.
Tasks	Image Retrieval
Published	2019-05-20
URL	https://arxiv.org/abs/1905.08139v3
PDF	https://arxiv.org/pdf/1905.08139v3.pdf
PWC	https://paperswithcode.com/paper/self-supervised-similarity-learning-for
Repo
Framework