January 30, 2020

3193 words 15 mins read

Paper Group ANR 252

CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments. Learning Cluster Structured Sparsity by Reweighting. Pixel DAG-Recurrent Neural Network for Spectral-Spatial Hyperspectral Image Classification. Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction. Quantitative Verification …

CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments


Title	CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments
Authors	Pierre Fournier, Olivier Sigaud, Cédric Colas, Mohamed Chetouani
Abstract	In this paper we study a new reinforcement learning setting where the environment is non-rewarding, contains several possibly related objects of various controllability, and where an apt agent Bob acts independently, with non-observable intentions. We argue that this setting defines a realistic scenario and we present a generic discrete-state discrete-action model of such environments. To learn in this environment, we propose an unsupervised reinforcement learning agent called CLIC for Curriculum Learning and Imitation for Control. CLIC learns to control individual objects in its environment, and imitates Bob’s interactions with these objects. It selects objects to focus on when training and imitating by maximizing its learning progress. We show that CLIC is an effective baseline in our new setting. It can effectively observe Bob to gain control of objects faster, even if Bob is not explicitly teaching. It can also follow Bob when he acts as a mentor and provides ordered demonstrations. Finally, when Bob controls objects that the agent cannot, or in presence of a hierarchy between objects in the environment, we show that CLIC ignores non-reproducible and already mastered interactions with objects, resulting in a greater benefit from imitation.
Tasks
Published	2019-01-28
URL	http://arxiv.org/abs/1901.09720v4
PDF	http://arxiv.org/pdf/1901.09720v4.pdf
PWC	https://paperswithcode.com/paper/clic-curriculum-learning-and-imitation-for
Repo
Framework

Learning Cluster Structured Sparsity by Reweighting


Title	Learning Cluster Structured Sparsity by Reweighting
Authors	Yulun Jiang, Lei Yu, Haijian Zhang, Zhou Liu
Abstract	Recently, the paradigm of unfolding iterative algorithms into finite-length feed-forward neural networks has achieved a great success in the area of sparse recovery. Benefit from available training data, the learned networks have achieved state-of-the-art performance in respect of both speed and accuracy. However, the structure behind sparsity, imposing constraint on the support of sparse signals, is often an essential prior knowledge but seldom considered in the existing networks. In this paper, we aim at bridging this gap. Specifically, exploiting the iterative reweighted $\ell_1$ minimization (IRL1) algorithm, we propose to learn the cluster structured sparsity (CSS) by rewegihting adaptively. In particular, we first unfold the Reweighted Iterative Shrinkage Algorithm (RwISTA) into an end-to-end trainable deep architecture termed as RW-LISTA. Then instead of the element-wise reweighting, the global and local reweighting manner are proposed for the cluster structured sparse learning. Numerical experiments further show the superiority of our algorithm against both classical algorithms and learning-based networks on different tasks.
Tasks	Sparse Learning
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05303v1
PDF	https://arxiv.org/pdf/1910.05303v1.pdf
PWC	https://paperswithcode.com/paper/learning-cluster-structured-sparsity-by-1
Repo
Framework

Pixel DAG-Recurrent Neural Network for Spectral-Spatial Hyperspectral Image Classification


Title	Pixel DAG-Recurrent Neural Network for Spectral-Spatial Hyperspectral Image Classification
Authors	Xiufang Li, Qigong Sun, Lingling Li, Zhongle Ren, Fang Liu, Licheng Jiao
Abstract	Exploiting rich spatial and spectral features contributes to improve the classification accuracy of hyperspectral images (HSIs). In this paper, based on the mechanism of the population receptive field (pRF) in human visual cortex, we further utilize the spatial correlation of pixels in images and propose pixel directed acyclic graph recurrent neural network (Pixel DAG-RNN) to extract and apply spectral-spatial features for HSIs classification. In our model, an undirected cyclic graph (UCG) is used to represent the relevance connectivity of pixels in an image patch, and four DAGs are used to approximate the spatial relationship of UCGs. In order to avoid overfitting, weight sharing and dropout are adopted. The higher classification performance of our model on HSIs classification has been verified by experiments on three benchmark data sets.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2019-06-09
URL	https://arxiv.org/abs/1906.03607v1
PDF	https://arxiv.org/pdf/1906.03607v1.pdf
PWC	https://paperswithcode.com/paper/pixel-dag-recurrent-neural-network-for
Repo
Framework

Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction


Title	Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction
Authors	Hongyao Tang, Jianye Hao, Guangyong Chen, Pengfei Chen, Zhaopeng Meng, Yaodong Yang, Li Wang
Abstract	Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochasticity of environmental dynamics and the quality of reward signals. In this paper, we propose a two-step understanding of value estimation from the perspective of future prediction, through decomposing the value function into a reward-independent future dynamics part and a policy-independent trajectory return part. We then derive a practical deep RL algorithm from the above decomposition, consisting of a convolutional trajectory representation model, a conditional variational dynamics model to predict the expected representation of future trajectory and a convex trajectory return model that maps a trajectory representation to its return. Our algorithm is evaluated in MuJoCo continuous control tasks and shows superior results under both common settings and delayed reward settings.
Tasks	Continuous Control, Future prediction
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11100v1
PDF	https://arxiv.org/pdf/1905.11100v1.pdf
PWC	https://paperswithcode.com/paper/disentangling-dynamics-and-returns-value
Repo
Framework

Quantitative Verification of Neural Networks And its Security Applications


Title	Quantitative Verification of Neural Networks And its Security Applications
Authors	Teodora Baluta, Shiqi Shen, Shweta Shinde, Kuldeep S. Meel, Prateek Saxena
Abstract	Neural networks are increasingly employed in safety-critical domains. This has prompted interest in verifying or certifying logically encoded properties of neural networks. Prior work has largely focused on checking existential properties, wherein the goal is to check whether there exists any input that violates a given property of interest. However, neural network training is a stochastic process, and many questions arising in their analysis require probabilistic and quantitative reasoning, i.e., estimating how many inputs satisfy a given property. To this end, our paper proposes a novel and principled framework to quantitative verification of logical properties specified over neural networks. Our framework is the first to provide PAC-style soundness guarantees, in that its quantitative estimates are within a controllable and bounded error from the true count. We instantiate our algorithmic framework by building a prototype tool called NPAQ that enables checking rich properties over binarized neural networks. We show how emerging security analyses can utilize our framework in 3 concrete point applications: quantifying robustness to adversarial inputs, efficacy of trojan attacks, and fairness/bias of given neural networks.
Tasks
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10395v1
PDF	https://arxiv.org/pdf/1906.10395v1.pdf
PWC	https://paperswithcode.com/paper/quantitative-verification-of-neural-networks
Repo
Framework

Colored Transparent Object Matting from a Single Image Using Deep Learning


Title	Colored Transparent Object Matting from a Single Image Using Deep Learning
Authors	Jamal Ahmed Rahim, Kwan-Yee Kenneth Wong
Abstract	This paper proposes a deep learning based method for colored transparent object matting from a single image. Existing approaches for transparent object matting often require multiple images and long processing times, which greatly hinder their applications on real-world transparent objects. The recently proposed TOM-Net can produce a matte for a colorless transparent object from a single image in a single fast feed-forward pass. In this paper, we extend TOM-Net to handle colored transparent object by modeling the intrinsic color of a transparent object with a color filter. We formulate the problem of colored transparent object matting as simultaneously estimating an object mask, a color filter, and a refractive flow field from a single image, and present a deep learning framework for learning this task. We create a large-scale synthetic dataset for training our network. We also capture a real dataset for evaluation. Experiments on both synthetic and real datasets show promising results, which demonstrate the effectiveness of our method.
Tasks
Published	2019-10-05
URL	https://arxiv.org/abs/1910.02222v1
PDF	https://arxiv.org/pdf/1910.02222v1.pdf
PWC	https://paperswithcode.com/paper/colored-transparent-object-matting-from-a
Repo
Framework

Predicting Electricity Consumption using Deep Recurrent Neural Networks


Title	Predicting Electricity Consumption using Deep Recurrent Neural Networks
Authors	Anupiya Nugaliyadde, Upeka Somaratne, Kok Wai Wong
Abstract	Electricity consumption has increased exponentially during the past few decades. This increase is heavily burdening the electricity distributors. Therefore, predicting the future demand for electricity consumption will provide an upper hand to the electricity distributor. Predicting electricity consumption requires many parameters. The paper presents two approaches with one using a Recurrent Neural Network (RNN) and another one using a Long Short Term Memory (LSTM) network, which only considers the previous electricity consumption to predict the future electricity consumption. These models were tested on the publicly available London smart meter dataset. To assess the applicability of the RNN and the LSTM network to predict electricity consumption, they were tested to predict for an individual house and a block of houses for a given time period. The predictions were done for daily, trimester and 13 months, which covers short term, mid-term and long term prediction. Both the RNN and the LSTM network have achieved an average Root Mean Square error of 0.1.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08182v1
PDF	https://arxiv.org/pdf/1909.08182v1.pdf
PWC	https://paperswithcode.com/paper/predicting-electricity-consumption-using-deep
Repo
Framework

On Applications of Bootstrap in Continuous Space Reinforcement Learning


Title	On Applications of Bootstrap in Continuous Space Reinforcement Learning
Authors	Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis
Abstract	In decision making problems for continuous state and action spaces, linear dynamical models are widely employed. Specifically, policies for stochastic linear systems subject to quadratic cost functions capture a large number of applications in reinforcement learning. Selected randomized policies have been studied in the literature recently that address the trade-off between identification and control. However, little is known about policies based on bootstrapping observed states and actions. In this work, we show that bootstrap-based policies achieve a square root scaling of regret with respect to time. We also obtain results on the accuracy of learning the model’s dynamics. Corroborative numerical analysis that illustrates the technical results is also provided.
Tasks	Decision Making
Published	2019-03-14
URL	http://arxiv.org/abs/1903.05803v2
PDF	http://arxiv.org/pdf/1903.05803v2.pdf
PWC	https://paperswithcode.com/paper/on-applications-of-bootstrap-in-continuous
Repo
Framework

Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning


Title	Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning
Authors	Kei Ota, Devesh K. Jha, Tomoaki Oiki, Mamoru Miura, Takashi Nammoto, Daniel Nikovski, Toshisada Mariyama
Abstract	In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known. Generating smooth, dynamically feasible trajectories could be difficult for such systems. Using sampling-based algorithms for motion planning may result in trajectories that are prone to undesirable control jumps. However, they can usually provide a good reference trajectory which a model-free reinforcement learning algorithm can then exploit by limiting the search domain and quickly finding a dynamically smooth trajectory. We use this idea to train a reinforcement learning agent to learn a dynamically smooth trajectory in a curriculum learning setting. Furthermore, for generalization, we parameterize the policies with goal locations, so that the agent can be trained for multiple goals simultaneously. We show result in both simulated environments as well as real experiments, for a $6$-DoF manipulator arm operated in position-controlled mode to validate the proposed idea. We compare the proposed ideas against a PID controller which is used to track a designed trajectory in configuration space. Our experiments show that our RL agent trained with a reference path outperformed a model-free PID controller of the type commonly used on many robotic platforms for trajectory tracking.
Tasks	Motion Planning
Published	2019-03-13
URL	https://arxiv.org/abs/1903.05751v2
PDF	https://arxiv.org/pdf/1903.05751v2.pdf
PWC	https://paperswithcode.com/paper/trajectory-optimization-for-unknown
Repo
Framework

Deep ensemble learning for Alzheimers disease classification


Title	Deep ensemble learning for Alzheimers disease classification
Authors	Ning An, Huitong Ding, Jiaoyun Yang, Rhoda Au, Ting Fang Alvin Ang
Abstract	Ensemble learning use multiple algorithms to obtain better predictive performance than any single one of its constituent algorithms could. With growing popularity of deep learning, researchers have started to ensemble them for various purposes. Few if any, however, has used the deep learning approach as a means to ensemble algorithms. This paper presents a deep ensemble learning framework which aims to harness deep learning algorithms to integrate multisource data and tap the wisdom of experts. At the voting layer, a sparse autoencoder is trained for feature learning to reduce the correlation of attributes and diversify the base classifiers ultimately. At the stacking layer, a nonlinear feature-weighted method based on deep belief networks is proposed to rank the base classifiers which may violate the conditional independence. Neural network is used as meta classifier. At the optimizing layer, under-sampling and threshold-moving are used to cope with cost-sensitive problem. Optimized predictions are obtained based on ensemble of probabilistic predictions by similarity calculation. The proposed deep ensemble learning framework is used for Alzheimers disease classification. Experiments with the clinical dataset from national Alzheimers coordinating center demonstrate that the classification accuracy of our proposed framework is 4% better than 6 well-known ensemble approaches as well as the standard stacking algorithm. Adequate coverage of more accurate diagnostic services can be provided by utilizing the wisdom of averaged physicians. This paper points out a new way to boost the primary care of Alzheimers disease from the view of machine learning.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12827v1
PDF	https://arxiv.org/pdf/1905.12827v1.pdf
PWC	https://paperswithcode.com/paper/deep-ensemble-learning-for-alzheimers-disease
Repo
Framework

Manipulation-skill Assessment from Videos with Spatial Attention Network


Title	Manipulation-skill Assessment from Videos with Spatial Attention Network
Authors	Zhenqiang Li, Yifei Huang, Minjie Cai, Yoichi Sato
Abstract	Recent advances in computer vision have made it possible to automatically assess from videos the manipulation skills of humans in performing a task, which breeds many important applications in domains such as health rehabilitation and manufacturing. Previous methods of video-based skill assessment did not consider the attention mechanism humans use in assessing videos, limiting their performance as only a small part of video regions is informative for skill assessment. Our motivation here is to estimate attention in videos that helps to focus on critically important video regions for better skill assessment. In particular, we propose a novel RNN-based spatial attention model that considers accumulated attention state from previous frames as well as high-level knowledge about the progress of an undergoing task. We evaluate our approach on a newly collected dataset of infant grasping task and four existing datasets of hand manipulation tasks. Experiment results demonstrate that state-of-the-art performance can be achieved by considering attention in automatic skill assessment.
Tasks
Published	2019-01-09
URL	http://arxiv.org/abs/1901.02579v2
PDF	http://arxiv.org/pdf/1901.02579v2.pdf
PWC	https://paperswithcode.com/paper/manipulation-skill-assessment-from-videos
Repo
Framework

Digital Normativity: A challenge for human subjectivization and free will


Title	Digital Normativity: A challenge for human subjectivization and free will
Authors	Éric Fourneret, Blaise Yvert
Abstract	Over the past decade, artificial intelligence has demonstrated its efficiency in many different applications and a huge number of algorithms have become central and ubiquitous in our life. Their growing interest is essentially based on their capability to synthesize and process large amounts of data, and to help humans making decisions in a world of increasing complexity. Yet, the effectiveness of algorithms in bringing more and more relevant recommendations to humans may start to compete with human-alone decisions based on values other than pure efficacy. Here, we examine this tension in light of the emergence of several forms of digital normativity, and analyze how this normative role of AI may influence the ability of humans to remain subject of their life. The advent of AI technology imposes a need to achieve a balance between concrete material progress and progress of the mind to avoid any form of servitude. It has become essential that an ethical reflection accompany the current developments of intelligent algorithms beyond the sole question of their social acceptability. Such reflection should be anchored where AI technologies are being developed as well as in educational programs where their implications can be explained.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09735v1
PDF	https://arxiv.org/pdf/1905.09735v1.pdf
PWC	https://paperswithcode.com/paper/digital-normativity-a-challenge-for-human
Repo
Framework

Sparse Canonical Correlation Analysis via Concave Minimization


Title	Sparse Canonical Correlation Analysis via Concave Minimization
Authors	Omid S. Solari, James B. Brown, Peter J. Bickel
Abstract	A new approach to the sparse Canonical Correlation Analysis (sCCA)is proposed with the aim of discovering interpretable associations in very high-dimensional multi-view, i.e.observations of multiple sets of variables on the same subjects, problems. Inspired by the sparse PCA approach of Journee et al. (2010), we also show that the sparse CCA formulation, while non-convex, is equivalent to a maximization program of a convex objective over a compact set for which we propose a first-order gradient method. This result helps us reduce the search space drastically to the boundaries of the set. Consequently, we propose a two-step algorithm, where we first infer the sparsity pattern of the canonical directions using our fast algorithm, then we shrink each view, i.e. observations of a set of covariates, to contain observations on the sets of covariates selected in the previous step, and compute their canonical directions via any CCA algorithm. We also introduceDirected Sparse CCA, which is able to find associations which are aligned with a specified experiment design, andMulti-View sCCA which is used to discover associations between multiple sets of covariates. Our simulations establish the superior convergence properties and computational efficiency of our algorithm as well as accuracy in terms of the canonical correlation and its ability to recover the supports of the canonical directions. We study the associations between metabolomics, trasncriptomics and microbiomics in a multi-omic study usingMuLe, which is an R-package that implements our approach, in order to form hypotheses on mechanisms of adaptations of Drosophila Melanogaster to high doses of environmental toxicants, specifically Atrazine, which is a commonly used chemical fertilizer.
Tasks
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07947v1
PDF	https://arxiv.org/pdf/1909.07947v1.pdf
PWC	https://paperswithcode.com/paper/sparse-canonical-correlation-analysis-via
Repo
Framework

Application of Clustering Analysis for Investigation of Food Accessibility


Title	Application of Clustering Analysis for Investigation of Food Accessibility
Authors	Rahul Srinivas Sucharitha, Seokcheon Lee
Abstract	Access to food assistance programs such as food pantries and food banks needs focus in order to mitigate food insecurity. Accessibility to the food assistance programs is impacted by demographics of the population and geography of the location. It hence becomes imperative to define and identify food assistance deserts (Under-served areas) within a given region to find out the ways to improve the accessibility of food. Food banks, the supplier of food to the food agencies serving the people, can manage its resources more efficiently by targeting the food assistance deserts and increase the food supply in those regions. This paper will examine the characteristics and structure of the food assistance network in the region of Ohio by presenting the possible reasons of food insecurity in this region and identify areas wherein food agencies are needed or may not be needed. Gaussian Mixture Model (GMM) clustering technique is employed to identify the possible reasons and address this problem of food accessibility.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.09453v1
PDF	https://arxiv.org/pdf/1909.09453v1.pdf
PWC	https://paperswithcode.com/paper/application-of-clustering-analysis-for
Repo
Framework

3D Deformable Convolutions for MRI classification


Title	3D Deformable Convolutions for MRI classification
Authors	Marina Pominova, Ekaterina Kondrateva, Maksim Sharaev, Sergey Pavlov, Alexander Bernstein, Evgeny Burnaev
Abstract	Deep learning convolutional neural networks have proved to be a powerful tool for MRI analysis. In current work, we explore the potential of the deformable convolutional deep neural network layers for MRI data classification. We propose new 3D deformable convolutions(d-convolutions), implement them in VoxResNet architecture and apply for structural MRI data classification. We show that 3D d-convolutions outperform standard ones and are effective for unprocessed 3D MR images being robust to particular geometrical properties of the data. Firstly proposed dVoxResNet architecture exhibits high potential for the use in MRI data classification.
Tasks
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01898v1
PDF	https://arxiv.org/pdf/1911.01898v1.pdf
PWC	https://paperswithcode.com/paper/3d-deformable-convolutions-for-mri
Repo
Framework