July 29, 2019

2992 words 15 mins read

Paper Group ANR 84

Small-footprint Keyword Spotting Using Deep Neural Network and Connectionist Temporal Classifier. Rhetorical relations for information retrieval. Proceedings First Workshop on Formal Verification of Autonomous Vehicles. Latent Hinge-Minimax Risk Minimization for Inference from a Small Number of Training Samples. Reflexive Regular Equivalence for Bi …

Small-footprint Keyword Spotting Using Deep Neural Network and Connectionist Temporal Classifier


Title	Small-footprint Keyword Spotting Using Deep Neural Network and Connectionist Temporal Classifier
Authors	Zhiming Wang, Xiaolong Li, Jun Zhou
Abstract	Mainly for the sake of solving the lack of keyword-specific data, we propose one Keyword Spotting (KWS) system using Deep Neural Network (DNN) and Connectionist Temporal Classifier (CTC) on power-constrained small-footprint mobile devices, taking full advantage of general corpus from continuous speech recognition which is of great amount. DNN is to directly predict the posterior of phoneme units of any personally customized key-phrase, and CTC to produce a confidence score of the given phoneme sequence as responsive decision-making mechanism. The CTC-KWS has competitive performance in comparison with purely DNN based keyword specific KWS, but not increasing any computational complexity.
Tasks	Decision Making, Keyword Spotting, Small-Footprint Keyword Spotting, Speech Recognition
Published	2017-09-12
URL	http://arxiv.org/abs/1709.03665v1
PDF	http://arxiv.org/pdf/1709.03665v1.pdf
PWC	https://paperswithcode.com/paper/small-footprint-keyword-spotting-using-deep
Repo
Framework

Rhetorical relations for information retrieval


Title	Rhetorical relations for information retrieval
Authors	Christina Lioma, Birger Larsen, Wei Lu
Abstract	Typically, every part in most coherent text has some plausible reason for its presence, some function that it performs to the overall semantics of the text. Rhetorical relations, e.g. contrast, cause, explanation, describe how the parts of a text are linked to each other. Knowledge about this socalled discourse structure has been applied successfully to several natural language processing tasks. This work studies the use of rhetorical relations for Information Retrieval (IR): Is there a correlation between certain rhetorical relations and retrieval performance? Can knowledge about a document’s rhetorical relations be useful to IR? We present a language model modification that considers rhetorical relations when estimating the relevance of a document to a query. Empirical evaluation of different versions of our model on TREC settings shows that certain rhetorical relations can benefit retrieval effectiveness notably (> 10% in mean average precision over a state-of-the-art baseline).
Tasks	Information Retrieval, Language Modelling
Published	2017-04-05
URL	http://arxiv.org/abs/1704.01599v1
PDF	http://arxiv.org/pdf/1704.01599v1.pdf
PWC	https://paperswithcode.com/paper/rhetorical-relations-for-information
Repo
Framework

Proceedings First Workshop on Formal Verification of Autonomous Vehicles


Title	Proceedings First Workshop on Formal Verification of Autonomous Vehicles
Authors	Lukas Bulwahn, Maryam Kamali, Sven Linker
Abstract	These are the proceedings of the workshop on Formal Verification of Autonomous Vehicles, held on September 19th, 2017 in Turin, Italy, as an affiliated workshop of the International Conference on integrated Formal Methods (iFM 2017). The workshop aim is to bring together researchers from the formal verification community that are developing formal methods for autonomous vehicles as well as researchers working, e.g., in the area of control theory or robotics, interested in applying verification techniques for designing and developing of autonomous vehicles.
Tasks	Autonomous Vehicles
Published	2017-09-07
URL	http://arxiv.org/abs/1709.02126v1
PDF	http://arxiv.org/pdf/1709.02126v1.pdf
PWC	https://paperswithcode.com/paper/proceedings-first-workshop-on-formal
Repo
Framework

Latent Hinge-Minimax Risk Minimization for Inference from a Small Number of Training Samples


Title	Latent Hinge-Minimax Risk Minimization for Inference from a Small Number of Training Samples
Authors	Dolev Raviv, Margarita Osadchy
Abstract	Deep Learning (DL) methods show very good performance when trained on large, balanced data sets. However, many practical problems involve imbalanced data sets, or/and classes with a small number of training samples. The performance of DL methods as well as more traditional classifiers drops significantly in such settings. Most of the existing solutions for imbalanced problems focus on customizing the data for training. A more principled solution is to use mixed Hinge-Minimax risk [19] specifically designed to solve binary problems with imbalanced training sets. Here we propose a Latent Hinge Minimax (LHM) risk and a training algorithm that generalizes this paradigm to an ensemble of hyperplanes that can form arbitrary complex, piecewise linear boundaries. To extract good features, we combine LHM model with CNN via transfer learning. To solve multi-class problem we map pre-trained category-specific LHM classifiers to a multi-class neural network and adjust the weights with very fast tuning. LHM classifier enables the use of unlabeled data in its training and the mapping allows for multi-class inference, resulting in a classifier that performs better than alternatives when trained on a small number of training samples.
Tasks	Transfer Learning
Published	2017-02-04
URL	http://arxiv.org/abs/1702.01293v1
PDF	http://arxiv.org/pdf/1702.01293v1.pdf
PWC	https://paperswithcode.com/paper/latent-hinge-minimax-risk-minimization-for
Repo
Framework

Reflexive Regular Equivalence for Bipartite Data


Title	Reflexive Regular Equivalence for Bipartite Data
Authors	Aaron Gerow, Mingyang Zhou, Stan Matwin, Feng Shi
Abstract	Bipartite data is common in data engineering and brings unique challenges, particularly when it comes to clustering tasks that impose on strong structural assumptions. This work presents an unsupervised method for assessing similarity in bipartite data. Similar to some co-clustering methods, the method is based on regular equivalence in graphs. The algorithm uses spectral properties of a bipartite adjacency matrix to estimate similarity in both dimensions. The method is reflexive in that similarity in one dimension is used to inform similarity in the other. Reflexive regular equivalence can also use the structure of transitivities – in a network sense – the contribution of which is controlled by the algorithm’s only free-parameter, $\alpha$. The method is completely unsupervised and can be used to validate assumptions of co-similarity, which are required but often untested, in co-clustering analyses. Three variants of the method with different normalizations are tested on synthetic data. The method is found to be robust to noise and well-suited to asymmetric co-similar structure, making it particularly informative for cluster analysis and recommendation in bipartite data of unknown structure. In experiments, the convergence and speed of the algorithm are found to be stable for different levels of noise. Real-world data from a network of malaria genes are analyzed, where the similarity produced by the reflexive method is shown to out-perform other measures’ ability to correctly classify genes.
Tasks
Published	2017-02-16
URL	http://arxiv.org/abs/1702.04956v1
PDF	http://arxiv.org/pdf/1702.04956v1.pdf
PWC	https://paperswithcode.com/paper/reflexive-regular-equivalence-for-bipartite
Repo
Framework

Geometry and Dynamics for Markov Chain Monte Carlo


Title	Geometry and Dynamics for Markov Chain Monte Carlo
Authors	Alessandro Barp, Francois-Xavier Briol, Anthony D. Kennedy, Mark Girolami
Abstract	Markov Chain Monte Carlo methods have revolutionised mathematical computation and enabled statistical inference within many previously intractable models. In this context, Hamiltonian dynamics have been proposed as an efficient way of building chains which can explore probability densities efficiently. The method emerges from physics and geometry and these links have been extensively studied by a series of authors through the last thirty years. However, there is currently a gap between the intuitions and knowledge of users of the methodology and our deep understanding of these theoretical foundations. The aim of this review is to provide a comprehensive introduction to the geometric tools used in Hamiltonian Monte Carlo at a level accessible to statisticians, machine learners and other users of the methodology with only a basic understanding of Monte Carlo methods. This will be complemented with some discussion of the most recent advances in the field which we believe will become increasingly relevant to applied scientists.
Tasks
Published	2017-05-08
URL	http://arxiv.org/abs/1705.02891v1
PDF	http://arxiv.org/pdf/1705.02891v1.pdf
PWC	https://paperswithcode.com/paper/geometry-and-dynamics-for-markov-chain-monte
Repo
Framework

A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning


Title	A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
Authors	Marc Lanctot, Vinicius Zambaldi, Audrunas Gruslys, Angeliki Lazaridou, Karl Tuyls, Julien Perolat, David Silver, Thore Graepel
Abstract	To achieve general intelligence, agents must learn how to interact with others in a shared environment: this is the challenge of multiagent reinforcement learning (MARL). The simplest form is independent reinforcement learning (InRL), where each agent treats its experience as part of its (non-stationary) environment. In this paper, we first observe that policies learned using InRL can overfit to the other agents’ policies during training, failing to sufficiently generalize during execution. We introduce a new metric, joint-policy correlation, to quantify this effect. We describe an algorithm for general MARL, based on approximate best responses to mixtures of policies generated using deep reinforcement learning, and empirical game-theoretic analysis to compute meta-strategies for policy selection. The algorithm generalizes previous ones such as InRL, iterated best response, double oracle, and fictitious play. Then, we present a scalable implementation which reduces the memory requirement using decoupled meta-solvers. Finally, we demonstrate the generality of the resulting policies in two partially observable settings: gridworld coordination games and poker.
Tasks
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00832v2
PDF	http://arxiv.org/pdf/1711.00832v2.pdf
PWC	https://paperswithcode.com/paper/a-unified-game-theoretic-approach-to
Repo
Framework

Rapid Near-Neighbor Interaction of High-dimensional Data via Hierarchical Clustering


Title	Rapid Near-Neighbor Interaction of High-dimensional Data via Hierarchical Clustering
Authors	Nikos Pitsianis, Dimitris Floros, Alexandros-Stavros Iliopoulos, Kostas Mylonakis, Nikos Sismanis, Xiaobai Sun
Abstract	Calculation of near-neighbor interactions among high dimensional, irregularly distributed data points is a fundamental task to many graph-based or kernel-based machine learning algorithms and applications. Such calculations, involving large, sparse interaction matrices, expose the limitation of conventional data-and-computation reordering techniques for improving space and time locality on modern computer memory hierarchies. We introduce a novel method for obtaining a matrix permutation that renders a desirable sparsity profile. The method is distinguished by the guiding principle to obtain a profile that is block-sparse with dense blocks. Our profile model and measure capture the essential properties affecting space and time locality, and permit variation in sparsity profile without imposing a restriction to a fixed pattern. The second distinction lies in an efficient algorithm for obtaining a desirable profile, via exploring and exploiting multi-scale cluster structure hidden in but intrinsic to the data. The algorithm accomplishes its task with key components for lower-dimensional embedding with data-specific principal feature axes, hierarchical data clustering, multi-level matrix compression storage, and multi-level interaction computations. We provide experimental results from case studies with two important data analysis algorithms. The resulting performance is remarkably comparable to the BLAS performance for the best-case interaction governed by a regularly banded matrix with the same sparsity.
Tasks
Published	2017-09-12
URL	http://arxiv.org/abs/1709.03671v1
PDF	http://arxiv.org/pdf/1709.03671v1.pdf
PWC	https://paperswithcode.com/paper/rapid-near-neighbor-interaction-of-high
Repo
Framework

Neural Signatures for Licence Plate Re-identification


Title	Neural Signatures for Licence Plate Re-identification
Authors	Abhinav Kumar, Shantanu Gupta, Vladimir Kozitsky, Sriganesh Madhvanath
Abstract	The problem of vehicle licence plate re-identification is generally considered as a one-shot image retrieval problem. The objective of this task is to learn a feature representation (called a “signature”) for licence plates. Incoming licence plate images are converted to signatures and matched to a previously collected template database through a distance measure. Then, the input image is recognized as the template whose signature is “nearest” to the input signature. The template database is restricted to contain only a single signature per unique licence plate for our problem. We measure the performance of deep convolutional net-based features adapted from face recognition on this task. In addition, we also test a hybrid approach combining the Fisher vector with a neural network-based embedding called “f2nn” trained with the Triplet loss function. We find that the hybrid approach performs comparably while providing computational benefits. The signature generated by the hybrid approach also shows higher generalizability to datasets more dissimilar to the training corpus.
Tasks	Face Recognition, Image Retrieval
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00282v1
PDF	http://arxiv.org/pdf/1712.00282v1.pdf
PWC	https://paperswithcode.com/paper/neural-signatures-for-licence-plate-re
Repo
Framework

HodgeRank with Information Maximization for Crowdsourced Pairwise Ranking Aggregation


Title	HodgeRank with Information Maximization for Crowdsourced Pairwise Ranking Aggregation
Authors	Qianqian Xu, Jiechao Xiong, Xi Chen, Qingming Huang, Yuan Yao
Abstract	Recently, crowdsourcing has emerged as an effective paradigm for human-powered large scale problem solving in various domains. However, task requester usually has a limited amount of budget, thus it is desirable to have a policy to wisely allocate the budget to achieve better quality. In this paper, we study the principle of information maximization for active sampling strategies in the framework of HodgeRank, an approach based on Hodge Decomposition of pairwise ranking data with multiple workers. The principle exhibits two scenarios of active sampling: Fisher information maximization that leads to unsupervised sampling based on a sequential maximization of graph algebraic connectivity without considering labels; and Bayesian information maximization that selects samples with the largest information gain from prior to posterior, which gives a supervised sampling involving the labels collected. Experiments show that the proposed methods boost the sampling efficiency as compared to traditional sampling schemes and are thus valuable to practical crowdsourcing experiments.
Tasks
Published	2017-11-16
URL	http://arxiv.org/abs/1711.05957v1
PDF	http://arxiv.org/pdf/1711.05957v1.pdf
PWC	https://paperswithcode.com/paper/hodgerank-with-information-maximization-for
Repo
Framework

Modelling Competitive Sports: Bradley-Terry-Élő Models for Supervised and On-Line Learning of Paired Competition Outcomes


Title	Modelling Competitive Sports: Bradley-Terry-Élő Models for Supervised and On-Line Learning of Paired Competition Outcomes
Authors	Franz J. Király, Zhaozhi Qian
Abstract	Prediction and modelling of competitive sports outcomes has received much recent attention, especially from the Bayesian statistics and machine learning communities. In the real world setting of outcome prediction, the seminal '{E}l\H{o} update still remains, after more than 50 years, a valuable baseline which is difficult to improve upon, though in its original form it is a heuristic and not a proper statistical “model”. Mathematically, the '{E}l\H{o} rating system is very closely related to the Bradley-Terry models, which are usually used in an explanatory fashion rather than in a predictive supervised or on-line learning setting. Exploiting this close link between these two model classes and some newly observed similarities, we propose a new supervised learning framework with close similarities to logistic regression, low-rank matrix completion and neural networks. Building on it, we formulate a class of structured log-odds models, unifying the desirable properties found in the above: supervised probabilistic prediction of scores and wins/draws/losses, batch/epoch and on-line learning, as well as the possibility to incorporate features in the prediction, without having to sacrifice simplicity, parsimony of the Bradley-Terry models, or computational efficiency of '{E}l\H{o}‘s original approach. We validate the structured log-odds modelling approach in synthetic experiments and English Premier League outcomes, where the added expressivity yields the best predictions reported in the state-of-art, close to the quality of contemporary betting odds.
Tasks	Low-Rank Matrix Completion, Matrix Completion
Published	2017-01-27
URL	http://arxiv.org/abs/1701.08055v1
PDF	http://arxiv.org/pdf/1701.08055v1.pdf
PWC	https://paperswithcode.com/paper/modelling-competitive-sports-bradley-terry
Repo
Framework

A survey of dimensionality reduction techniques based on random projection


Title	A survey of dimensionality reduction techniques based on random projection
Authors	Haozhe Xie, Jie Li, Hanqing Xue
Abstract	Dimensionality reduction techniques play important roles in the analysis of big data. Traditional dimensionality reduction approaches, such as principal component analysis (PCA) and linear discriminant analysis (LDA), have been studied extensively in the past few decades. However, as the dimensionality of data increases, the computational cost of traditional dimensionality reduction methods grows exponentially, and the computation becomes prohibitively intractable. These drawbacks have triggered the development of random projection (RP) techniques, which map high-dimensional data onto a low-dimensional subspace with extremely reduced time cost. However, the RP transformation matrix is generated without considering the intrinsic structure of the original data and usually leads to relatively high distortion. Therefore, in recent years, methods based on RP have been proposed to address this problem. In this paper, we summarize the methods used in different situations to help practitioners to employ the proper techniques for their specific applications. Meanwhile, we enumerate the benefits and limitations of the various methods and provide further references for researchers to develop novel RP-based approaches.
Tasks	Dimensionality Reduction
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04371v4
PDF	http://arxiv.org/pdf/1706.04371v4.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-dimensionality-reduction-1
Repo
Framework

Deep Learning: Generalization Requires Deep Compositional Feature Space Design


Title	Deep Learning: Generalization Requires Deep Compositional Feature Space Design
Authors	Mrinal Haloi
Abstract	Generalization error defines the discriminability and the representation power of a deep model. In this work, we claim that feature space design using deep compositional function plays a significant role in generalization along with explicit and implicit regularizations. Our claims are being established with several image classification experiments. We show that the information loss due to convolution and max pooling can be marginalized with the compositional design, improving generalization performance. Also, we will show that learning rate decay acts as an implicit regularizer in deep model training.
Tasks	Image Classification
Published	2017-06-06
URL	http://arxiv.org/abs/1706.01983v2
PDF	http://arxiv.org/pdf/1706.01983v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-generalization-requires-deep
Repo
Framework

Guided Interaction Exploration in Artifact-centric Process Models


Title	Guided Interaction Exploration in Artifact-centric Process Models
Authors	Maikel L. van Eck, Natalia Sidorova, Wil M. P. van der Aalst
Abstract	Artifact-centric process models aim to describe complex processes as a collection of interacting artifacts. Recent development in process mining allow for the discovery of such models. However, the focus is often on the representation of the individual artifacts rather than their interactions. Based on event data we can automatically discover composite state machines representing artifact-centric processes. Moreover, we provide ways of visualizing and quantifying interactions among different artifacts. For example, we are able to highlight strongly correlated behaviours in different artifacts. The approach has been fully implemented as a ProM plug-in; the CSM Miner provides an interactive artifact-centric process discovery tool focussing on interactions. The approach has been evaluated using real life data sets, including the personal loan and overdraft process of a Dutch financial institution.
Tasks
Published	2017-06-07
URL	http://arxiv.org/abs/1706.02109v1
PDF	http://arxiv.org/pdf/1706.02109v1.pdf
PWC	https://paperswithcode.com/paper/guided-interaction-exploration-in-artifact
Repo
Framework

Video Object Segmentation using Tracked Object Proposals


Title	Video Object Segmentation using Tracked Object Proposals
Authors	Gilad Sharir, Eddie Smolyansky, Itamar Friedman
Abstract	We present an approach to semi-supervised video object segmentation, in the context of the DAVIS 2017 challenge. Our approach combines category-based object detection, category-independent object appearance segmentation and temporal object tracking. We are motivated by the fact that the objects semantic category tends not to change throughout the video while its appearance and location can vary considerably. In order to capture the specific object appearance independent of its category, for each video we train a fully convolutional network using augmentations of the given annotated frame. We refine the appearance segmentation mask with the bounding boxes provided either by a semantic object detection network, when applicable, or by a previous frame prediction. By introducing a temporal continuity constraint on the detected boxes, we are able to improve the object segmentation mask of the appearance network and achieve competitive results on the DAVIS datasets.
Tasks	Object Detection, Object Tracking, Semantic Segmentation, Semi-supervised Video Object Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06545v1
PDF	http://arxiv.org/pdf/1707.06545v1.pdf
PWC	https://paperswithcode.com/paper/video-object-segmentation-using-tracked
Repo
Framework