July 28, 2019

2964 words 14 mins read

Paper Group ANR 369

Faster Reinforcement Learning Using Active Simulators. Statistical evaluation of visual quality metrics for image denoising. Optimization on Product Submanifolds of Convolution Kernels. Phase Transitions in Image Denoising via Sparsely Coding Convolutional Neural Networks. Opinion Mining on Non-English Short Text. A Deep Network Model for Paraphras …

Faster Reinforcement Learning Using Active Simulators


Title	Faster Reinforcement Learning Using Active Simulators
Authors	Vikas Jain, Theja Tulabandhula
Abstract	In this work, we propose several online methods to build a \emph{learning curriculum} from a given set of target-task-specific training tasks in order to speed up reinforcement learning (RL). These methods can decrease the total training time needed by an RL agent compared to training on the target task from scratch. Unlike traditional transfer learning, we consider creating a sequence from several training tasks in order to provide the most benefit in terms of reducing the total time to train. Our methods utilize the learning trajectory of the agent on the curriculum tasks seen so far to decide which tasks to train on next. An attractive feature of our methods is that they are weakly coupled to the choice of the RL algorithm as well as the transfer learning method. Further, when there is domain information available, our methods can incorporate such knowledge to further speed up the learning. We experimentally show that these methods can be used to obtain suitable learning curricula that speed up the overall training time on two different domains.
Tasks	Transfer Learning
Published	2017-03-22
URL	http://arxiv.org/abs/1703.07853v2
PDF	http://arxiv.org/pdf/1703.07853v2.pdf
PWC	https://paperswithcode.com/paper/faster-reinforcement-learning-using-active
Repo
Framework

Statistical evaluation of visual quality metrics for image denoising


Title	Statistical evaluation of visual quality metrics for image denoising
Authors	Karen Egiazarian, Mykola Ponomarenko, Vladimir Lukin, Oleg Ieremeiem
Abstract	This paper studies the problem of full reference visual quality assessment of denoised images with a special emphasis on images with low contrast and noise-like texture. Denoising of such images together with noise removal often results in image details loss or smoothing. A new test image database, FLT, containing 75 noise-free “reference” images and 300 filtered (“distorted”) images is developed. Each reference image, corrupted by an additive white Gaussian noise, is denoised by the BM3D filter with four different values of threshold parameter (four levels of noise suppression). After carrying out a perceptual quality assessment of distorted images, the mean opinion scores (MOS) are obtained and compared with the values of known full reference quality metrics. As a result, the Spearman Rank Order Correlation Coefficient (SROCC) between PSNR values and MOS has a value close to zero, and SROCC between values of known full-reference image visual quality metrics and MOS does not exceed 0.82 (which is reached by a new visual quality metric proposed in this paper). The FLT dataset is more complex than earlier datasets used for assessment of visual quality for image denoising. Thus, it can be effectively used to design new image visual quality metrics for image denoising.
Tasks	Denoising, Image Denoising
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00693v1
PDF	http://arxiv.org/pdf/1711.00693v1.pdf
PWC	https://paperswithcode.com/paper/statistical-evaluation-of-visual-quality
Repo
Framework

Optimization on Product Submanifolds of Convolution Kernels


Title	Optimization on Product Submanifolds of Convolution Kernels
Authors	Mete Ozay, Takayuki Okatani
Abstract	Recent advances in optimization methods used for training convolutional neural networks (CNNs) with kernels, which are normalized according to particular constraints, have shown remarkable success. This work introduces an approach for training CNNs using ensembles of joint spaces of kernels constructed using different constraints. For this purpose, we address a problem of optimization on ensembles of products of submanifolds (PEMs) of convolution kernels. To this end, we first propose three strategies to construct ensembles of PEMs in CNNs. Next, we expound their geometric properties (metric and curvature properties) in CNNs. We make use of our theoretical results by developing a geometry-aware SGD algorithm (G-SGD) for optimization on ensembles of PEMs to train CNNs. Moreover, we analyze convergence properties of G-SGD considering geometric properties of PEMs. In the experimental analyses, we employ G-SGD to train CNNs on Cifar-10, Cifar-100 and Imagenet datasets. The results show that geometric adaptive step size computation methods of G-SGD can improve training loss and convergence properties of CNNs. Moreover, we observe that classification performance of baseline CNNs can be boosted using G-SGD on ensembles of PEMs identified by multiple constraints.
Tasks
Published	2017-01-22
URL	http://arxiv.org/abs/1701.06123v2
PDF	http://arxiv.org/pdf/1701.06123v2.pdf
PWC	https://paperswithcode.com/paper/optimization-on-product-submanifolds-of
Repo
Framework

Phase Transitions in Image Denoising via Sparsely Coding Convolutional Neural Networks


Title	Phase Transitions in Image Denoising via Sparsely Coding Convolutional Neural Networks
Authors	Jacob Carroll, Nils Carlson, Garrett T. Kenyon
Abstract	Neural networks are analogous in many ways to spin glasses, systems which are known for their rich set of dynamics and equally complex phase diagrams. We apply well-known techniques in the study of spin glasses to a convolutional sparsely encoding neural network and observe power law finite-size scaling behavior in the sparsity and reconstruction error as the network denoises 32$\times$32 RGB CIFAR-10 images. This finite-size scaling indicates the presence of a continuous phase transition at a critical value of this sparsity. By using the power law scaling relations inherent to finite-size scaling, we can determine the optimal value of sparsity for any network size by tuning the system to the critical point and operate the system at the minimum denoising error.
Tasks	Denoising, Image Denoising
Published	2017-10-26
URL	http://arxiv.org/abs/1710.09875v1
PDF	http://arxiv.org/pdf/1710.09875v1.pdf
PWC	https://paperswithcode.com/paper/phase-transitions-in-image-denoising-via
Repo
Framework

Opinion Mining on Non-English Short Text


Title	Opinion Mining on Non-English Short Text
Authors	Esra Akbas
Abstract	As the type and the number of such venues increase, automated analysis of sentiment on textual resources has become an essential data mining task. In this paper, we investigate the problem of mining opinions on the collection of informal short texts. Both positive and negative sentiment strength of texts are detected. We focus on a non-English language that has few resources for text mining. This approach would help enhance the sentiment analysis in languages where a list of opinionated words does not exist. We propose a new method projects the text into dense and low dimensional feature vectors according to the sentiment strength of the words. We detect the mixture of positive and negative sentiments on a multi-variant scale. Empirical evaluation of the proposed framework on Turkish tweets shows that our approach gets good results for opinion mining.
Tasks	Opinion Mining, Sentiment Analysis
Published	2017-03-31
URL	http://arxiv.org/abs/1704.00016v2
PDF	http://arxiv.org/pdf/1704.00016v2.pdf
PWC	https://paperswithcode.com/paper/opinion-mining-on-non-english-short-text
Repo
Framework

A Deep Network Model for Paraphrase Detection in Short Text Messages


Title	A Deep Network Model for Paraphrase Detection in Short Text Messages
Authors	Basant Agarwal, Heri Ramampiaro, Helge Langseth, Massimiliano Ruocco
Abstract	This paper is concerned with paraphrase detection. The ability to detect similar sentences written in natural language is crucial for several applications, such as text mining, text summarization, plagiarism detection, authorship authentication and question answering. Given two sentences, the objective is to detect whether they are semantically identical. An important insight from this work is that existing paraphrase systems perform well when applied on clean texts, but they do not necessarily deliver good performance against noisy texts. Challenges with paraphrase detection on user generated short texts, such as Twitter, include language irregularity and noise. To cope with these challenges, we propose a novel deep neural network-based approach that relies on coarse-grained sentence modeling using a convolutional neural network and a long short-term memory model, combined with a specific fine-grained word-level similarity matching model. Our experimental results show that the proposed approach outperforms existing state-of-the-art approaches on user-generated noisy social media data, such as Twitter texts, and achieves highly competitive performance on a cleaner corpus.
Tasks	Question Answering, Text Summarization
Published	2017-12-07
URL	http://arxiv.org/abs/1712.02820v1
PDF	http://arxiv.org/pdf/1712.02820v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-network-model-for-paraphrase-detection
Repo
Framework

Artificial Intelligence Approaches To UCAV Autonomy


Title	Artificial Intelligence Approaches To UCAV Autonomy
Authors	Amir Husain, Bruce Porter
Abstract	This paper covers a number of approaches that leverage Artificial Intelligence algorithms and techniques to aid Unmanned Combat Aerial Vehicle (UCAV) autonomy. An analysis of current approaches to autonomous control is provided followed by an exploration of how these techniques can be extended and enriched with AI techniques including Artificial Neural Networks (ANN), Ensembling and Reinforcement Learning (RL) to evolve control strategies for UCAVs.
Tasks
Published	2017-01-24
URL	http://arxiv.org/abs/1701.07103v1
PDF	http://arxiv.org/pdf/1701.07103v1.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-approaches-to-ucav
Repo
Framework

Non-negative Tensor Factorization for Human Behavioral Pattern Mining in Online Games


Title	Non-negative Tensor Factorization for Human Behavioral Pattern Mining in Online Games
Authors	Anna Sapienza, Alessandro Bessi, Emilio Ferrara
Abstract	Multiplayer online battle arena has become a popular game genre. It also received increasing attention from our research community because they provide a wealth of information about human interactions and behaviors. A major problem is extracting meaningful patterns of activity from this type of data, in a way that is also easy to interpret. Here, we propose to exploit tensor decomposition techniques, and in particular Non-negative Tensor Factorization, to discover hidden correlated behavioral patterns of play in a popular game: League of Legends. We first collect the entire gaming history of a group of about one thousand players, totaling roughly $100K$ matches. By applying our methodological framework, we then separate players into groups that exhibit similar features and playing strategies, as well as similar temporal trajectories, i.e., behavioral progressions over the course of their gaming history: this will allow us to investigate how players learn and improve their skills.
Tasks	League of Legends
Published	2017-02-19
URL	http://arxiv.org/abs/1702.05695v1
PDF	http://arxiv.org/pdf/1702.05695v1.pdf
PWC	https://paperswithcode.com/paper/non-negative-tensor-factorization-for-human
Repo
Framework

Nonparanormal Information Estimation


Title	Nonparanormal Information Estimation
Authors	Shashank Singh, Barnabás Pøczos
Abstract	We study the problem of using i.i.d. samples from an unknown multivariate probability distribution $p$ to estimate the mutual information of $p$. This problem has recently received attention in two settings: (1) where $p$ is assumed to be Gaussian and (2) where $p$ is assumed only to lie in a large nonparametric smoothness class. Estimators proposed for the Gaussian case converge in high dimensions when the Gaussian assumption holds, but are brittle, failing dramatically when $p$ is not Gaussian. Estimators proposed for the nonparametric case fail to converge with realistic sample sizes except in very low dimensions. As a result, there is a lack of robust mutual information estimators for many realistic data. To address this, we propose estimators for mutual information when $p$ is assumed to be a nonparanormal (a.k.a., Gaussian copula) model, a semiparametric compromise between Gaussian and nonparametric extremes. Using theoretical bounds and experiments, we show these estimators strike a practical balance between robustness and scaling with dimensionality.
Tasks
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07803v1
PDF	http://arxiv.org/pdf/1702.07803v1.pdf
PWC	https://paperswithcode.com/paper/nonparanormal-information-estimation
Repo
Framework

CNN-Based Projected Gradient Descent for Consistent Image Reconstruction


Title	CNN-Based Projected Gradient Descent for Consistent Image Reconstruction
Authors	Harshit Gupta, Kyong Hwan Jin, Ha Q. Nguyen, Michael T. McCann, Michael Unser
Abstract	We present a new method for image reconstruction which replaces the projector in a projected gradient descent (PGD) with a convolutional neural network (CNN). CNNs trained as high-dimensional (image-to-image) regressors have recently been used to efficiently solve inverse problems in imaging. However, these approaches lack a feedback mechanism to enforce that the reconstructed image is consistent with the measurements. This is crucial for inverse problems, and more so in biomedical imaging, where the reconstructions are used for diagnosis. In our scheme, the gradient descent enforces measurement consistency, while the CNN recursively projects the solution closer to the space of desired reconstruction images. We provide a formal framework to ensure that the classical PGD converges to a local minimizer of a non-convex constrained least-squares problem. When the projector is replaced with a CNN, we propose a relaxed PGD, which always converges. Finally, we propose a simple scheme to train a CNN to act like a projector. Our experiments on sparse view Computed Tomography (CT) reconstruction for both noiseless and noisy measurements show an improvement over the total-variation (TV) method and a recent CNN-based technique.
Tasks	Computed Tomography (CT), Image Reconstruction
Published	2017-09-06
URL	http://arxiv.org/abs/1709.01809v1
PDF	http://arxiv.org/pdf/1709.01809v1.pdf
PWC	https://paperswithcode.com/paper/cnn-based-projected-gradient-descent-for
Repo
Framework

Enhanced Emotion Enabled Cognitive Agent Based Rear End Collision Avoidance Controller for Autonomous Vehicles


Title	Enhanced Emotion Enabled Cognitive Agent Based Rear End Collision Avoidance Controller for Autonomous Vehicles
Authors	Faisal Riaz, Muaz A. Niazi
Abstract	Rear end collisions are deadliest in nature and cause most of traffic casualties and injuries. In the existing research, many rear end collision avoidance solutions have been proposed. However, the problem with these proposed solutions is that they are highly dependent on precise mathematical models. Whereas, the real road driving is influenced by non-linear factors such as road surface situations, driver reaction time, pedestrian flow and vehicle dynamics, hence obtaining the accurate mathematical model of the vehicle control system is challenging. This problem with precise control based rear end collision avoidance schemes has been addressed using fuzzy logic, but the excessive number of fuzzy rules straightforwardly prejudice their efficiency. Furthermore, these fuzzy logic based controllers have been proposed without using proper agent based modeling that helps in mimicking the functions of an artificial human driver executing these fuzzy rules. Keeping in view these limitations, we have proposed an Enhanced Emotion Enabled Cognitive Agent (EEEC_Agent) based controller that helps the Autonomous Vehicles (AVs) to perform rear end collision avoidance with less number of rules, designed after fear emotion, and high efficiency. To introduce a fear emotion generation mechanism in EEEC_Agent, Orton, Clore & Collins (OCC) model has been employed. The fear generation mechanism of EEEC_Agent has been verified using NetLogo simulation. Furthermore, practical validation of EEEC_Agent functions has been performed using specially built prototype AV platform. Eventually, the qualitative comparative study with existing state of the art research works reflect that proposed model outperforms recent research.
Tasks	Autonomous Vehicles
Published	2017-08-06
URL	http://arxiv.org/abs/1708.01930v1
PDF	http://arxiv.org/pdf/1708.01930v1.pdf
PWC	https://paperswithcode.com/paper/enhanced-emotion-enabled-cognitive-agent
Repo
Framework

Prior Knowledge based mutation prioritization towards causal variant finding in rare disease


Title	Prior Knowledge based mutation prioritization towards causal variant finding in rare disease
Authors	Vasundhara Dehiya, Jaya Thomas, Lee Sael
Abstract	How do we determine the mutational effects in exome sequencing data with little or no statistical evidence? Can protein structural information fill in the gap of not having enough statistical evidence? In this work, we answer the two questions with the goal towards determining pathogenic effects of rare variants in rare disease. We take the approach of determining the importance of point mutation loci focusing on protein structure features. The proposed structure-based features contain information about geometric, physicochemical, and functional information of mutation loci and those of structural neighbors of the loci. The performance of the structure-based features trained on 80% of HumDiv and tested on 20% of HumDiv and on ClinVar datasets showed high levels of discernibility in the mutation’s pathogenic or benign effects: F score of 0.71 and 0.68 respectively using multi-layer perceptron. Combining structure- and sequence-based feature further improve the accuracy: F score of 0.86 (HumDiv) and 0.75 (ClinVar). Also, careful examination of the rare variants in rare diseases cases showed that structure-based features are important in discerning importance of variant loci.
Tasks
Published	2017-10-10
URL	http://arxiv.org/abs/1710.03399v1
PDF	http://arxiv.org/pdf/1710.03399v1.pdf
PWC	https://paperswithcode.com/paper/prior-knowledge-based-mutation-prioritization
Repo
Framework

Knowledge Base Completion: Baselines Strike Back


Title	Knowledge Base Completion: Baselines Strike Back
Authors	Rudolf Kadlec, Ondrej Bajgar, Jan Kleindienst
Abstract	Many papers have been published on the knowledge base completion task in the past few years. Most of these introduce novel architectures for relation learning that are evaluated on standard datasets such as FB15k and WN18. This paper shows that the accuracy of almost all models published on the FB15k can be outperformed by an appropriately tuned baseline - our reimplementation of the DistMult model. Our findings cast doubt on the claim that the performance improvements of recent models are due to architectural changes as opposed to hyper-parameter tuning or different training objectives. This should prompt future research to re-consider how the performance of models is evaluated and reported.
Tasks	Knowledge Base Completion
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10744v1
PDF	http://arxiv.org/pdf/1705.10744v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-base-completion-baselines-strike
Repo
Framework

ENWalk: Learning Network Features for Spam Detection in Twitter


Title	ENWalk: Learning Network Features for Spam Detection in Twitter
Authors	K C Santosh, Suman Kalyan Maity, Arjun Mukherjee
Abstract	Social medias are increasing their influence with the vast public information leading to their active use for marketing by the companies and organizations. Such marketing promotions are difficult to identify unlike the traditional medias like TV and newspaper. So, it is very much important to identify the promoters in the social media. Although, there are active ongoing researches, existing approaches are far from solving the problem. To identify such imposters, it is very much important to understand their strategies of social circle creation and dynamics of content posting. Are there any specific spammer types? How successful are each types? We analyze these questions in the light of social relationships in Twitter. Our analyses discover two types of spammers and their relationships with the dynamics of content posts. Our results discover novel dynamics of spamming which are intuitive and arguable. We propose ENWalk, a framework to detect the spammers by learning the feature representations of the users in the social media. We learn the feature representations using the random walks biased on the spam dynamics. Experimental results on large-scale twitter network and the corresponding tweets show the effectiveness of our approach that outperforms the existing approaches
Tasks
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03404v1
PDF	http://arxiv.org/pdf/1704.03404v1.pdf
PWC	https://paperswithcode.com/paper/enwalk-learning-network-features-for-spam
Repo
Framework

Training Language Models Using Target-Propagation


Title	Training Language Models Using Target-Propagation
Authors	Sam Wiseman, Sumit Chopra, Marc’Aurelio Ranzato, Arthur Szlam, Ruoyu Sun, Soumith Chintala, Nicolas Vasilache
Abstract	While Truncated Back-Propagation through Time (BPTT) is the most popular approach to training Recurrent Neural Networks (RNNs), it suffers from being inherently sequential (making parallelization difficult) and from truncating gradient flow between distant time-steps. We investigate whether Target Propagation (TPROP) style approaches can address these shortcomings. Unfortunately, extensive experiments suggest that TPROP generally underperforms BPTT, and we end with an analysis of this phenomenon, and suggestions for future work.
Tasks
Published	2017-02-15
URL	http://arxiv.org/abs/1702.04770v1
PDF	http://arxiv.org/pdf/1702.04770v1.pdf
PWC	https://paperswithcode.com/paper/training-language-models-using-target
Repo
Framework