July 28, 2019

2882 words 14 mins read

Paper Group ANR 231

Transforming Bell’s Inequalities into State Classifiers with Machine Learning. Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates. Evolution and Analysis of Embodied Spiking Neural Networks Reveals Task-Specific Clusters of Effective Networks. Entropy-based Pruning for Learning Bayesian Networks using BIC. Genetic …

Transforming Bell’s Inequalities into State Classifiers with Machine Learning


Title	Transforming Bell’s Inequalities into State Classifiers with Machine Learning
Authors	Yue-Chi Ma, Man-Hong Yung
Abstract	Quantum information science has profoundly changed the ways we understand, store, and process information. A major challenge in this field is to look for an efficient means for classifying quantum state. For instance, one may want to determine if a given quantum state is entangled or not. However, the process of a complete characterization of quantum states, known as quantum state tomography, is a resource-consuming operation in general. An attractive proposal would be the use of Bell’s inequalities as an entanglement witness, where only partial information of the quantum state is needed. The problem is that entanglement is necessary but not sufficient for violating Bell’s inequalities, making it an unreliable state classifier. Here we aim at solving this problem by the methods of machine learning. More precisely, given a family of quantum states, we randomly picked a subset of it to construct a quantum-state classifier, accepting only partial information of each quantum state. Our results indicated that these transformed Bell-type inequalities can perform significantly better than the original Bell’s inequalities in classifying entangled states. We further extended our analysis to three-qubit and four-qubit systems, performing classification of quantum states into multiple species. These results demonstrate how the tools in machine learning can be applied to solving problems in quantum information science.
Tasks	Quantum State Tomography
Published	2017-05-02
URL	http://arxiv.org/abs/1705.00813v1
PDF	http://arxiv.org/pdf/1705.00813v1.pdf
PWC	https://paperswithcode.com/paper/transforming-bells-inequalities-into-state
Repo
Framework

Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates


Title	Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates
Authors	Jun Liu, Amir Shahroudy, Dong Xu, Alex C. Kot, Gang Wang
Abstract	Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional configurations of human body joints for better analysis of human activities in the skeletal data. The proposed work extends this idea to spatial domain as well as temporal domain to better analyze the hidden sources of action-related information within the human skeleton sequences in both of these domains simultaneously. Based on the pictorial structure of Kinect’s skeletal data, an effective tree-structure based traversal framework is also proposed. In order to deal with the noise in the skeletal data, a new gating mechanism within LSTM module is introduced, with which the network can learn the reliability of the sequential data and accordingly adjust the effect of the input data on the updating procedure of the long-term context representation stored in the unit’s memory cell. Moreover, we introduce a novel multi-modal feature fusion strategy within the LSTM unit in this paper. The comprehensive experimental results on seven challenging benchmark datasets for human action recognition demonstrate the effectiveness of the proposed method.
Tasks	One-Shot 3D Action Recognition, Skeleton Based Action Recognition, Temporal Action Localization
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08276v1
PDF	http://arxiv.org/pdf/1706.08276v1.pdf
PWC	https://paperswithcode.com/paper/skeleton-based-action-recognition-using
Repo
Framework

Evolution and Analysis of Embodied Spiking Neural Networks Reveals Task-Specific Clusters of Effective Networks


Title	Evolution and Analysis of Embodied Spiking Neural Networks Reveals Task-Specific Clusters of Effective Networks
Authors	Madhavun Candadai Vasu, Eduardo J. Izquierdo
Abstract	Elucidating principles that underlie computation in neural networks is currently a major research topic of interest in neuroscience. Transfer Entropy (TE) is increasingly used as a tool to bridge the gap between network structure, function, and behavior in fMRI studies. Computational models allow us to bridge the gap even further by directly associating individual neuron activity with behavior. However, most computational models that have analyzed embodied behaviors have employed non-spiking neurons. On the other hand, computational models that employ spiking neural networks tend to be restricted to disembodied tasks. We show for the first time the artificial evolution and TE-analysis of embodied spiking neural networks to perform a cognitively-interesting behavior. Specifically, we evolved an agent controlled by an Izhikevich neural network to perform a visual categorization task. The smallest networks capable of performing the task were found by repeating evolutionary runs with different network sizes. Informational analysis of the best solution revealed task-specific TE-network clusters, suggesting that within-task homogeneity and across-task heterogeneity were key to behavioral success. Moreover, analysis of the ensemble of solutions revealed that task-specificity of TE-network clusters correlated with fitness. This provides an empirically testable hypothesis that links network structure to behavior.
Tasks
Published	2017-04-13
URL	http://arxiv.org/abs/1704.04199v2
PDF	http://arxiv.org/pdf/1704.04199v2.pdf
PWC	https://paperswithcode.com/paper/evolution-and-analysis-of-embodied-spiking
Repo
Framework

Entropy-based Pruning for Learning Bayesian Networks using BIC


Title	Entropy-based Pruning for Learning Bayesian Networks using BIC
Authors	Cassio P. de Campos, Mauro Scanagatta, Giorgio Corani, Marco Zaffalon
Abstract	For decomposable score-based structure learning of Bayesian networks, existing approaches first compute a collection of candidate parent sets for each variable and then optimize over this collection by choosing one parent set for each variable without creating directed cycles while maximizing the total score. We target the task of constructing the collection of candidate parent sets when the score of choice is the Bayesian Information Criterion (BIC). We provide new non-trivial results that can be used to prune the search space of candidate parent sets of each node. We analyze how these new results relate to previous ideas in the literature both theoretically and empirically. We show in experiments with UCI data sets that gains can be significant. Since the new pruning rules are easy to implement and have low computational costs, they can be promptly integrated into all state-of-the-art methods for structure learning of Bayesian networks.
Tasks
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06194v1
PDF	http://arxiv.org/pdf/1707.06194v1.pdf
PWC	https://paperswithcode.com/paper/entropy-based-pruning-for-learning-bayesian
Repo
Framework

Genetic Algorithms for Evolving Deep Neural Networks


Title	Genetic Algorithms for Evolving Deep Neural Networks
Authors	Eli David, Iddo Greental
Abstract	In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and propose a GA-assisted method for deep learning. Our experimental results indicate that this GA-assisted approach improves the performance of a deep autoencoder, producing a sparser neural network.
Tasks
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07655v1
PDF	http://arxiv.org/pdf/1711.07655v1.pdf
PWC	https://paperswithcode.com/paper/genetic-algorithms-for-evolving-deep-neural
Repo
Framework

Dependency resolution and semantic mining using Tree Adjoining Grammars for Tamil Language


Title	Dependency resolution and semantic mining using Tree Adjoining Grammars for Tamil Language
Authors	Vijay Krishna Menon, S Rajendran, M Anandkumar, K P Soman
Abstract	Tree adjoining grammars (TAGs) provide an ample tool to capture syntax of many Indian languages. Tamil represents a special challenge to computational formalisms as it has extensive agglutinative morphology and a comparatively difficult argument structure. Modelling Tamil syntax and morphology using TAG is an interesting problem which has not been in focus even though TAGs are over 4 decades old, since its inception. Our research with Tamil TAGs have shown us that we can not only represent syntax of the language, but to an extent mine out semantics through dependency resolution of the sentence. But in order to demonstrate this phenomenal property, we need to parse Tamil language sentences using TAGs we have built and through parsing obtain a derivation we could use to resolve dependencies, thus proving the semantic property. We use an in-house developed pseudo lexical TAG chart parser; algorithm given by Schabes and Joshi (1988), for generating derivations of sentences. We do not use any statistics to rank out ambiguous derivations but rather use all of them to understand the mentioned semantic relation with in TAGs for Tamil. We shall also present a brief parser analysis for the completeness of our discussions.
Tasks
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05611v1
PDF	http://arxiv.org/pdf/1704.05611v1.pdf
PWC	https://paperswithcode.com/paper/dependency-resolution-and-semantic-mining
Repo
Framework

Using Satellite Imagery for Good: Detecting Communities in Desert and Mapping Vaccination Activities


Title	Using Satellite Imagery for Good: Detecting Communities in Desert and Mapping Vaccination Activities
Authors	Anza Shakeel, Mohsen Ali
Abstract	Deep convolutional neural networks (CNNs) have outperformed existing object recognition and detection algorithms. On the other hand satellite imagery captures scenes that are diverse. This paper describes a deep learning approach that analyzes a geo referenced satellite image and efficiently detects built structures in it. A Fully Convolution Network (FCN) is trained on low resolution Google earth satellite imagery in order to achieve end result. The detected built communities are then correlated with the vaccination activity that has furnished some useful statistics.
Tasks	Object Recognition
Published	2017-05-12
URL	http://arxiv.org/abs/1705.04451v1
PDF	http://arxiv.org/pdf/1705.04451v1.pdf
PWC	https://paperswithcode.com/paper/using-satellite-imagery-for-good-detecting
Repo
Framework

Improved Learning in Evolution Strategies via Sparser Inter-Agent Network Topologies


Title	Improved Learning in Evolution Strategies via Sparser Inter-Agent Network Topologies
Authors	Dhaval Adjodah, Dan Calacci, Yan Leng, Peter Krafft, Esteban Moro, Alex Pentland
Abstract	We draw upon a previously largely untapped literature on human collective intelligence as a source of inspiration for improving deep learning. Implicit in many algorithms that attempt to solve Deep Reinforcement Learning (DRL) tasks is the network of processors along which parameter values are shared. So far, existing approaches have implicitly utilized fully-connected networks, in which all processors are connected. However, the scientific literature on human collective intelligence suggests that complete networks may not always be the most effective information network structures for distributed search through complex spaces. Here we show that alternative topologies can improve deep neural network training: we find that sparser networks learn higher rewards faster, leading to learning improvements at lower communication costs.
Tasks
Published	2017-11-30
URL	http://arxiv.org/abs/1711.11180v2
PDF	http://arxiv.org/pdf/1711.11180v2.pdf
PWC	https://paperswithcode.com/paper/improved-learning-in-evolution-strategies-via
Repo
Framework

The energy landscape of a simple neural network


Title	The energy landscape of a simple neural network
Authors	Anthony Collins Gamst, Alden Walker
Abstract	We explore the energy landscape of a simple neural network. In particular, we expand upon previous work demonstrating that the empirical complexity of fitted neural networks is vastly less than a naive parameter count would suggest and that this implicit regularization is actually beneficial for generalization from fitted models.
Tasks
Published	2017-06-21
URL	http://arxiv.org/abs/1706.07101v1
PDF	http://arxiv.org/pdf/1706.07101v1.pdf
PWC	https://paperswithcode.com/paper/the-energy-landscape-of-a-simple-neural
Repo
Framework

Face Deidentification with Generative Deep Neural Networks


Title	Face Deidentification with Generative Deep Neural Networks
Authors	Blaž Meden, Refik Can Mallı, Sebastjan Fabijan, Hazım Kemal Ekenel, Vitomir Štruc, Peter Peer
Abstract	Face deidentification is an active topic amongst privacy and security researchers. Early deidentification methods relying on image blurring or pixelization were replaced in recent years with techniques based on formal anonymity models that provide privacy guaranties and at the same time aim at retaining certain characteristics of the data even after deidentification. The latter aspect is particularly important, as it allows to exploit the deidentified data in applications for which identity information is irrelevant. In this work we present a novel face deidentification pipeline, which ensures anonymity by synthesizing artificial surrogate faces using generative neural networks (GNNs). The generated faces are used to deidentify subjects in images or video, while preserving non-identity-related aspects of the data and consequently enabling data utilization. Since generative networks are very adaptive and can utilize a diverse set of parameters (pertaining to the appearance of the generated output in terms of facial expressions, gender, race, etc.), they represent a natural choice for the problem of face deidentification. To demonstrate the feasibility of our approach, we perform experiments using automated recognition tools and human annotators. Our results show that the recognition performance on deidentified images is close to chance, suggesting that the deidentification process based on GNNs is highly effective.
Tasks
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09376v1
PDF	http://arxiv.org/pdf/1707.09376v1.pdf
PWC	https://paperswithcode.com/paper/face-deidentification-with-generative-deep
Repo
Framework

Spectral Filter Tracking


Title	Spectral Filter Tracking
Authors	Zhen Cui, You yi Cai, Wen ming Zheng, Jian Yang
Abstract	Visual object tracking is a challenging computer vision task with numerous real-world applications. Here we propose a simple but efficient Spectral Filter Tracking (SFT)method. To characterize rotational and translation invariance of tracking targets, the candidate image region is models as a pixelwise grid graph. Instead of the conventional graph matching, we convert the tracking into a plain least square regression problem to estimate the best center coordinate of the target. But different from the holistic regression of correlation filter based methods, SFT can operate on localized surrounding regions of each pixel (i.e.,vertex) by using spectral graph filters, which thus is more robust to resist local variations and cluttered background.To bypass the eigenvalue decomposition problem of the graph Laplacian matrix L, we parameterize spectral graph filters as the polynomial of L by spectral graph theory, in which L k exactly encodes a k-hop local neighborhood of each vertex. Finally, the filter parameters (i.e., polynomial coefficients) as well as feature projecting functions are jointly integrated into the regression model.
Tasks	Graph Matching, Object Tracking, Visual Object Tracking
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05553v1
PDF	http://arxiv.org/pdf/1707.05553v1.pdf
PWC	https://paperswithcode.com/paper/spectral-filter-tracking
Repo
Framework

Evaluating Machine Translation Performance on Chinese Idioms with a Blacklist Method


Title	Evaluating Machine Translation Performance on Chinese Idioms with a Blacklist Method
Authors	Yutong Shao, Rico Sennrich, Bonnie Webber, Federico Fancellu
Abstract	Idiom translation is a challenging problem in machine translation because the meaning of idioms is non-compositional, and a literal (word-by-word) translation is likely to be wrong. In this paper, we focus on evaluating the quality of idiom translation of MT systems. We introduce a new evaluation method based on an idiom-specific blacklist of literal translations, based on the insight that the occurrence of any blacklisted words in the translation output indicates a likely translation error. We introduce a dataset, CIBB (Chinese Idioms Blacklists Bank), and perform an evaluation of a state-of-the-art Chinese-English neural MT system. Our evaluation confirms that a sizable number of idioms in our test set are mistranslated (46.1%), that literal translation error is a common error type, and that our blacklist method is effective at identifying literal translation errors.
Tasks	Machine Translation
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07646v3
PDF	http://arxiv.org/pdf/1711.07646v3.pdf
PWC	https://paperswithcode.com/paper/evaluating-machine-translation-performance-on
Repo
Framework

Non-Linear Reduced Modeling by Generalized Kernel-Based Dynamic Mode Decomposition


Title	Non-Linear Reduced Modeling by Generalized Kernel-Based Dynamic Mode Decomposition
Authors	Patrick Héas, Cédric Herzet, Benoit Combès
Abstract	Reduced modeling of a computationally demanding dynamical system aims at approximating its trajectories, while optimizing the trade-off between accuracy and computational complexity. In this work, we propose to achieve such an approximation by first embedding the trajectories in a reproducing kernel Hilbert space (RKHS), which exhibits appealing approximation and computational capabilities, and then solving the associated reduced model problem. More specifically, we propose a new efficient algorithm for data-driven reduced modeling of non-linear dynamics based on linear approximations in a RKHS. This algorithm takes advantage of the closed-form solution of a low-rank constraint optimization problem while exploiting advantageously kernel-based computations. Reduced modeling with this algorithm reveals a gain in approximation accuracy, as shown by numerical simulations, and in complexity with respect to existing approaches.
Tasks
Published	2017-10-30
URL	https://arxiv.org/abs/1710.10919v5
PDF	https://arxiv.org/pdf/1710.10919v5.pdf
PWC	https://paperswithcode.com/paper/kernel-based-methods-for-non-linear-reduced
Repo
Framework

Dynamic Graph Generation Network: Generating Relational Knowledge from Diagrams


Title	Dynamic Graph Generation Network: Generating Relational Knowledge from Diagrams
Authors	Daesik Kim, Youngjoon Yoo, Jeesoo Kim, Sangkuk Lee, Nojun Kwak
Abstract	In this work, we introduce a new algorithm for analyzing a diagram, which contains visual and textual information in an abstract and integrated way. Whereas diagrams contain richer information compared with individual image-based or language-based data, proper solutions for automatically understanding them have not been proposed due to their innate characteristics of multi-modality and arbitrariness of layouts. To tackle this problem, we propose a unified diagram-parsing network for generating knowledge from diagrams based on an object detector and a recurrent neural network designed for a graphical structure. Specifically, we propose a dynamic graph-generation network that is based on dynamic memory and graph theory. We explore the dynamics of information in a diagram with activation of gates in gated recurrent unit (GRU) cells. On publicly available diagram datasets, our model demonstrates a state-of-the-art result that outperforms other baselines. Moreover, further experiments on question answering shows potentials of the proposed method for various applications.
Tasks	Graph Generation, Question Answering
Published	2017-11-27
URL	http://arxiv.org/abs/1711.09528v1
PDF	http://arxiv.org/pdf/1711.09528v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-graph-generation-network-generating
Repo
Framework

Training object class detectors with click supervision


Title	Training object class detectors with click supervision
Authors	Dim P. Papadopoulos, Jasper R. R. Uijlings, Frank Keller, Vittorio Ferrari
Abstract	Training object class detectors typically requires a large set of images with objects annotated by bounding boxes. However, manually drawing bounding boxes is very time consuming. In this paper we greatly reduce annotation time by proposing center-click annotations: we ask annotators to click on the center of an imaginary bounding box which tightly encloses the object instance. We then incorporate these clicks into existing Multiple Instance Learning techniques for weakly supervised object localization, to jointly localize object bounding boxes over all training images. Extensive experiments on PASCAL VOC 2007 and MS COCO show that: (1) our scheme delivers high-quality detectors, performing substantially better than those produced by weakly supervised techniques, with a modest extra annotation effort; (2) these detectors in fact perform in a range close to those trained from manually drawn bounding boxes; (3) as the center-click task is very fast, our scheme reduces total annotation time by 9x to 18x.
Tasks	Multiple Instance Learning, Object Localization, Weakly-Supervised Object Localization
Published	2017-04-20
URL	http://arxiv.org/abs/1704.06189v2
PDF	http://arxiv.org/pdf/1704.06189v2.pdf
PWC	https://paperswithcode.com/paper/training-object-class-detectors-with-click
Repo
Framework