July 29, 2019

3214 words 16 mins read

Paper Group ANR 143

Quantum Low Entropy based Associative Reasoning or QLEAR Learning. Lattice embeddings between types of fuzzy sets. Closed-valued fuzzy sets. Ontology based system to guide internship assignment process. Improving Efficiency in Convolutional Neural Network with Multilinear Filters. Sample-efficient Actor-Critic Reinforcement Learning with Supervised …

Quantum Low Entropy based Associative Reasoning or QLEAR Learning


Title	Quantum Low Entropy based Associative Reasoning or QLEAR Learning
Authors	Marko V. Jankovic
Abstract	In this paper, we propose the classification method based on a learning paradigm we are going to call Quantum Low Entropy based Associative Reasoning or QLEAR learning. The approach is based on the idea that classification can be understood as supervised clustering, where a quantum entropy in the context of the quantum probabilistic model, will be used as a “capturer” (measure, or external index), of the “natural structure” of the data. By using quantum entropy we do not make any assumption about linear separability of the data that are going to be classified. The basic idea is to find close neighbors to a query sample and then use relative change in the quantum entropy as a measure of similarity of the newly arrived sample with the representatives of interest. In other words, method is based on calculation of quantum entropy of the referent system and its relative change with the addition of the newly arrived sample. Referent system consists of vectors that represent individual classes and that are the most similar, in Euclidean distance sense, to the vector that is analyzed. Here, we analyze the classification problem in the context of measuring similarities to prototype examples of categories. While nearest neighbor classifiers are natural in this setting, they suffer from the problem of high variance (in bias-variance decomposition) in the case of limited sampling. Alternatively, one could use machine learning techniques (like support vector machines) but they involve time-consuming optimization. Here we propose a hybrid of nearest neighbor and machine learning technique which deals naturally with the multi-class setting, has reasonable computational complexity both in training and at run time, and yields excellent results in practice.
Tasks
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10503v1
PDF	http://arxiv.org/pdf/1705.10503v1.pdf
PWC	https://paperswithcode.com/paper/quantum-low-entropy-based-associative
Repo
Framework

Lattice embeddings between types of fuzzy sets. Closed-valued fuzzy sets


Title	Lattice embeddings between types of fuzzy sets. Closed-valued fuzzy sets
Authors	F. J. Lobillo, Luis Merino, Gabriel Navarro, Evangelina Santos
Abstract	In this paper we deal with the problem of extending Zadeh’s operators on fuzzy sets (FSs) to interval-valued (IVFSs), set-valued (SVFSs) and type-2 (T2FSs) fuzzy sets. Namely, it is known that seeing FSs as SVFSs, or T2FSs, whose membership degrees are singletons is not order-preserving. We then describe a family of lattice embeddings from FSs to SVFSs. Alternatively, if the former singleton viewpoint is required, we reformulate the intersection on hesitant fuzzy sets and introduce what we have called closed-valued fuzzy sets. This new type of fuzzy sets extends standard union and intersection on FSs. In addition, it allows handling together membership degrees of different nature as, for instance, closed intervals and finite sets. Finally, all these constructions are viewed as T2FSs forming a chain of lattices.
Tasks
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03752v1
PDF	http://arxiv.org/pdf/1711.03752v1.pdf
PWC	https://paperswithcode.com/paper/lattice-embeddings-between-types-of-fuzzy
Repo
Framework

Ontology based system to guide internship assignment process


Title	Ontology based system to guide internship assignment process
Authors	Abir M ‘Baya, Jannik Laval, Nejib Moalla, Yacine Ouzrout, Abdelaziz Bouras
Abstract	Internship assignment is a complicated process for universities since it is necessary to take into account a multiplicity of variables to establish a compromise between companies’ requirements and student competencies acquired during the university training. These variables build up a complex relations map that requires the formulation of an exhaustive and rigorous conceptual scheme. In this research a domain ontological model is presented as support to the student’s decision making for opportunities of University studies level of the University Lumiere Lyon 2 (ULL) education system. The ontology is designed and created using methodological approach offering the possibility of improving the progressive creation, capture and knowledge articulation. In this paper, we draw a balance taking the demands of the companies across the capabilities of the students. This will be done through the establishment of an ontological model of an educational learners’ profile and the internship postings which are written in a free text and using uncontrolled vocabulary. Furthermore, we outline the process of semantic matching which improves the quality of query results.
Tasks	Decision Making
Published	2017-01-18
URL	http://arxiv.org/abs/1701.05059v1
PDF	http://arxiv.org/pdf/1701.05059v1.pdf
PWC	https://paperswithcode.com/paper/ontology-based-system-to-guide-internship
Repo
Framework

Improving Efficiency in Convolutional Neural Network with Multilinear Filters


Title	Improving Efficiency in Convolutional Neural Network with Multilinear Filters
Authors	Dat Thanh Tran, Alexandros Iosifidis, Moncef Gabbouj
Abstract	The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices. However, current deep net architectures are heavy with millions of parameters and require billions of floating point operations. Several works have been developed to compress a pre-trained deep network to reduce memory footprint and, possibly, computation. Instead of compressing a pre-trained network, in this work, we propose a generic neural network layer structure employing multilinear projection as the primary feature extractor. The proposed architecture requires several times less memory as compared to the traditional Convolutional Neural Networks (CNN), while inherits the similar design principles of a CNN. In addition, the proposed architecture is equipped with two computation schemes that enable computation reduction or scalability. Experimental results show the effectiveness of our compact projection that outperforms traditional CNN, while requiring far fewer parameters.
Tasks
Published	2017-09-28
URL	http://arxiv.org/abs/1709.09902v3
PDF	http://arxiv.org/pdf/1709.09902v3.pdf
PWC	https://paperswithcode.com/paper/improving-efficiency-in-convolutional-neural
Repo
Framework

Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management


Title	Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
Authors	Pei-Hao Su, Pawel Budzianowski, Stefan Ultes, Milica Gasic, Steve Young
Abstract	Deep reinforcement learning (RL) methods have significant potential for dialogue policy optimisation. However, they suffer from a poor performance in the early stages of learning. This is especially problematic for on-line learning with real users. Two approaches are introduced to tackle this problem. Firstly, to speed up the learning process, two sample-efficient neural networks algorithms: trust region actor-critic with experience replay (TRACER) and episodic natural actor-critic with experience replay (eNACER) are presented. For TRACER, the trust region helps to control the learning step size and avoid catastrophic model changes. For eNACER, the natural gradient identifies the steepest ascent direction in policy space to speed up the convergence. Both models employ off-policy learning with experience replay to improve sample-efficiency. Secondly, to mitigate the cold start issue, a corpus of demonstration data is utilised to pre-train the models prior to on-line reinforcement learning. Combining these two approaches, we demonstrate a practical approach to learn deep RL-based dialogue policies and demonstrate their effectiveness in a task-oriented information seeking domain.
Tasks	Dialogue Management
Published	2017-07-01
URL	http://arxiv.org/abs/1707.00130v2
PDF	http://arxiv.org/pdf/1707.00130v2.pdf
PWC	https://paperswithcode.com/paper/sample-efficient-actor-critic-reinforcement
Repo
Framework

Refining Image Categorization by Exploiting Web Images and General Corpus


Title	Refining Image Categorization by Exploiting Web Images and General Corpus
Authors	Yazhou Yao, Jian Zhang, Fumin Shen, Xiansheng Hua, Wankou Yang, Zhenmin Tang
Abstract	Studies show that refining real-world categories into semantic subcategories contributes to better image modeling and classification. Previous image sub-categorization work relying on labeled images and WordNet’s hierarchy is not only labor-intensive, but also restricted to classify images into NOUN subcategories. To tackle these problems, in this work, we exploit general corpus information to automatically select and subsequently classify web images into semantic rich (sub-)categories. The following two major challenges are well studied: 1) noise in the labels of subcategories derived from the general corpus; 2) noise in the labels of images retrieved from the web. Specifically, we first obtain the semantic refinement subcategories from the text perspective and remove the noise by the relevance-based approach. To suppress the search error induced noisy images, we then formulate image selection and classifier learning as a multi-class multi-instance learning problem and propose to solve the employed problem by the cutting-plane algorithm. The experiments show significant performance gains by using the generated data of our way on both image categorization and sub-categorization tasks. The proposed approach also consistently outperforms existing weakly supervised and web-supervised approaches.
Tasks	Image Categorization
Published	2017-03-16
URL	http://arxiv.org/abs/1703.05451v1
PDF	http://arxiv.org/pdf/1703.05451v1.pdf
PWC	https://paperswithcode.com/paper/refining-image-categorization-by-exploiting
Repo
Framework

WASSA-2017 Shared Task on Emotion Intensity


Title	WASSA-2017 Shared Task on Emotion Intensity
Authors	Saif M. Mohammad, Felipe Bravo-Marquez
Abstract	We present the first shared task on detecting the intensity of emotion felt by the speaker of a tweet. We create the first datasets of tweets annotated for anger, fear, joy, and sadness intensities using a technique called best–worst scaling (BWS). We show that the annotations lead to reliable fine-grained intensity scores (rankings of tweets by intensity). The data was partitioned into training, development, and test sets for the competition. Twenty-two teams participated in the shared task, with the best system obtaining a Pearson correlation of 0.747 with the gold intensity scores. We summarize the machine learning setups, resources, and tools used by the participating teams, with a focus on the techniques and resources that are particularly useful for the task. The emotion intensity dataset and the shared task are helping improve our understanding of how we convey more or less intense emotions through language.
Tasks
Published	2017-08-11
URL	http://arxiv.org/abs/1708.03700v1
PDF	http://arxiv.org/pdf/1708.03700v1.pdf
PWC	https://paperswithcode.com/paper/wassa-2017-shared-task-on-emotion-intensity
Repo
Framework

Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification


Title	Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
Authors	Lin Wu, Yang Wang
Abstract	Given a pedestrian image as a query, the purpose of person re-identification is to identify the correct match from a large collection of gallery images depicting the same person captured by disjoint camera views. The critical challenge is how to construct a robust yet discriminative feature representation to capture the compounded variations in pedestrian appearance. To this end, deep learning methods have been proposed to extract hierarchical features against extreme variability of appearance. However, existing methods in this category generally neglect the efficiency in the matching stage whereas the searching speed of a re-identification system is crucial in real-world applications. In this paper, we present a novel deep hashing framework with Convolutional Neural Networks (CNNs) for fast person re-identification. Technically, we simultaneously learn both CNN features and hash functions/codes to get robust yet discriminative features and similarity-preserving hash codes. Thereby, person re-identification can be resolved by efficiently computing and ranking the Hamming distances between images. A structured loss function defined over positive pairs and hard negatives is proposed to formulate a novel optimization problem so that fast convergence and more stable optimized solution can be obtained. Extensive experiments on two benchmarks CUHK03 \cite{FPNN} and Market-1501 \cite{Market1501} show that the proposed deep architecture is efficacy over state-of-the-arts.
Tasks	Person Re-Identification
Published	2017-02-14
URL	http://arxiv.org/abs/1702.04179v3
PDF	http://arxiv.org/pdf/1702.04179v3.pdf
PWC	https://paperswithcode.com/paper/structured-deep-hashing-with-convolutional
Repo
Framework

Structured learning and detailed interpretation of minimal object images


Title	Structured learning and detailed interpretation of minimal object images
Authors	Guy Ben-Yosef, Liav Assif, Shimon Ullman
Abstract	We model the process of human full interpretation of object images, namely the ability to identify and localize all semantic features and parts that are recognized by human observers. The task is approached by dividing the interpretation of the complete object to the interpretation of multiple reduced but interpretable local regions. We model interpretation by a structured learning framework, in which there are primitive components and relations that play a useful role in local interpretation by humans. To identify useful components and relations used in the interpretation process, we consider the interpretation of minimal configurations, namely reduced local regions that are minimal in the sense that further reduction will turn them unrecognizable and uninterpretable. We show experimental results of our model, and results of predicting and testing relations that were useful to the model via transformed minimal images.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.11151v1
PDF	http://arxiv.org/pdf/1711.11151v1.pdf
PWC	https://paperswithcode.com/paper/structured-learning-and-detailed
Repo
Framework

Towards a Knowledge Graph based Speech Interface


Title	Towards a Knowledge Graph based Speech Interface
Authors	Ashwini Jaya Kumar, Sören Auer, Christoph Schmidt, Joachim köhler
Abstract	Applications which use human speech as an input require a speech interface with high recognition accuracy. The words or phrases in the recognised text are annotated with a machine-understandable meaning and linked to knowledge graphs for further processing by the target application. These semantic annotations of recognised words can be represented as a subject-predicate-object triples which collectively form a graph often referred to as a knowledge graph. This type of knowledge representation facilitates to use speech interfaces with any spoken input application, since the information is represented in logical, semantic form, retrieving and storing can be followed using any web standard query languages. In this work, we develop a methodology for linking speech input to knowledge graphs and study the impact of recognition errors in the overall process. We show that for a corpus with lower WER, the annotation and linking of entities to the DBpedia knowledge graph is considerable. DBpedia Spotlight, a tool to interlink text documents with the linked open data is used to link the speech recognition output to the DBpedia knowledge graph. Such a knowledge-based speech recognition interface is useful for applications such as question answering or spoken dialog systems.
Tasks	Knowledge Graphs, Question Answering, Speech Recognition
Published	2017-05-23
URL	http://arxiv.org/abs/1705.09222v1
PDF	http://arxiv.org/pdf/1705.09222v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-knowledge-graph-based-speech
Repo
Framework

Risk-Sensitive Cooperative Games for Human-Machine Systems


Title	Risk-Sensitive Cooperative Games for Human-Machine Systems
Authors	Agostino Capponi, Reza Ghanadan, Matt Stern
Abstract	Autonomous systems can substantially enhance a human’s efficiency and effectiveness in complex environments. Machines, however, are often unable to observe the preferences of the humans that they serve. Despite the fact that the human’s and machine’s objectives are aligned, asymmetric information, along with heterogeneous sensitivities to risk by the human and machine, make their joint optimization process a game with strategic interactions. We propose a framework based on risk-sensitive dynamic games; the human seeks to optimize her risk-sensitive criterion according to her true preferences, while the machine seeks to adaptively learn the human’s preferences and at the same time provide a good service to the human. We develop a class of performance measures for the proposed framework based on the concept of regret. We then evaluate their dependence on the risk-sensitivity and the degree of uncertainty. We present applications of our framework to self-driving taxis, and robo-financial advising.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09580v1
PDF	http://arxiv.org/pdf/1705.09580v1.pdf
PWC	https://paperswithcode.com/paper/risk-sensitive-cooperative-games-for-human
Repo
Framework

Learning under $p$-Tampering Attacks


Title	Learning under $p$-Tampering Attacks
Authors	Saeed Mahloujifar, Dimitrios I. Diochnos, Mohammad Mahmoody
Abstract	Recently, Mahloujifar and Mahmoody (TCC’17) studied attacks against learning algorithms using a special case of Valiant’s malicious noise, called $p$-tampering, in which the adversary gets to change any training example with independent probability $p$ but is limited to only choose malicious examples with correct labels. They obtained $p$-tampering attacks that increase the error probability in the so called targeted poisoning model in which the adversary’s goal is to increase the loss of the trained hypothesis over a particular test example. At the heart of their attack was an efficient algorithm to bias the expected value of any bounded real-output function through $p$-tampering. In this work, we present new biasing attacks for increasing the expected value of bounded real-valued functions. Our improved biasing attacks, directly imply improved $p$-tampering attacks against learners in the targeted poisoning model. As a bonus, our attacks come with considerably simpler analysis. We also study the possibility of PAC learning under $p$-tampering attacks in the non-targeted (aka indiscriminate) setting where the adversary’s goal is to increase the risk of the generated hypothesis (for a random test example). We show that PAC learning is possible under $p$-tampering poisoning attacks essentially whenever it is possible in the realizable setting without the attacks. We further show that PAC learning under “correct-label” adversarial noise is not possible in general, if the adversary could choose the (still limited to only $p$ fraction of) tampered examples that she substitutes with adversarially chosen ones. Our formal model for such “bounded-budget” tampering attackers is inspired by the notions of (strong) adaptive corruption in secure multi-party computation.
Tasks
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03707v4
PDF	http://arxiv.org/pdf/1711.03707v4.pdf
PWC	https://paperswithcode.com/paper/learning-under-p-tampering-attacks
Repo
Framework

Neural Network Based Nonlinear Weighted Finite Automata


Title	Neural Network Based Nonlinear Weighted Finite Automata
Authors	Tianyu Li, Guillaume Rabusseau, Doina Precup
Abstract	Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models. Given the recent successes of nonlinear models in machine learning, it is natural to wonder whether ex-tending WFA to the nonlinear setting would be beneficial. In this paper, we propose a novel model of neural network based nonlinearWFA model (NL-WFA) along with a learning algorithm. Our learning algorithm is inspired by the spectral learning algorithm for WFAand relies on a nonlinear decomposition of the so-called Hankel matrix, by means of an auto-encoder network. The expressive power of NL-WFA and the proposed learning algorithm are assessed on both synthetic and real-world data, showing that NL-WFA can lead to smaller model sizes and infer complex grammatical structures from data.
Tasks
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04380v2
PDF	http://arxiv.org/pdf/1709.04380v2.pdf
PWC	https://paperswithcode.com/paper/neural-network-based-nonlinear-weighted
Repo
Framework

Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks


Title	Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks
Authors	Surbhi Goel, Adam Klivans
Abstract	We consider the problem of learning function classes computed by neural networks with various activations (e.g. ReLU or Sigmoid), a task believed to be computationally intractable in the worst-case. A major open problem is to understand the minimal assumptions under which these classes admit provably efficient algorithms. In this work we show that a natural distributional assumption corresponding to {\em eigenvalue decay} of the Gram matrix yields polynomial-time algorithms in the non-realizable setting for expressive classes of networks (e.g. feed-forward networks of ReLUs). We make no assumptions on the structure of the network or the labels. Given sufficiently-strong polynomial eigenvalue decay, we obtain {\em fully}-polynomial time algorithms in {\em all} the relevant parameters with respect to square-loss. Milder decay assumptions also lead to improved algorithms. This is the first purely distributional assumption that leads to polynomial-time algorithms for networks of ReLUs, even with one hidden layer. Further, unlike prior distributional assumptions (e.g., the marginal distribution is Gaussian), eigenvalue decay has been observed in practice on common data sets.
Tasks
Published	2017-08-11
URL	http://arxiv.org/abs/1708.03708v1
PDF	http://arxiv.org/pdf/1708.03708v1.pdf
PWC	https://paperswithcode.com/paper/eigenvalue-decay-implies-polynomial-time
Repo
Framework

Calibrating Black Box Classification Models through the Thresholding Method


Title	Calibrating Black Box Classification Models through the Thresholding Method
Authors	Arun Srinivasan
Abstract	In high-dimensional classification settings, we wish to seek a balance between high power and ensuring control over a desired loss function. In many settings, the points most likely to be misclassified are those who lie near the decision boundary of the given classification method. Often, these uninformative points should not be classified as they are noisy and do not exhibit strong signals. In this paper, we introduce the Thresholding Method to parameterize the problem of determining which points exhibit strong signals and should be classified. We demonstrate the empirical performance of this novel calibration method in providing loss function control at a desired level, as well as explore how the method assuages the effect of overfitting. We explore the benefits of error control through the Thresholding Method in difficult, high-dimensional, simulated settings. Finally, we show the flexibility of the Thresholding Method through applying the method in a variety of real data settings.
Tasks	Calibration
Published	2017-05-20
URL	http://arxiv.org/abs/1705.07348v2
PDF	http://arxiv.org/pdf/1705.07348v2.pdf
PWC	https://paperswithcode.com/paper/calibrating-black-box-classification-models
Repo
Framework