May 6, 2019

2494 words 12 mins read

Paper Group ANR 165

Range-based argumentation semantics as 2-valued models. Adaptability of Neural Networks on Varying Granularity IR Tasks. $f$-Divergence Inequalities via Functional Domination. Tool and Phase recognition using contextual CNN features. Implementing a Relevance Tracker Module. A Probabilistic Optimum-Path Forest Classifier for Binary Classification Pr …

Range-based argumentation semantics as 2-valued models


Title	Range-based argumentation semantics as 2-valued models
Authors	Mauricio Osorio, Juan Carlos Nieves
Abstract	Characterizations of semi-stable and stage extensions in terms of 2-valued logical models are presented. To this end, the so-called GL-supported and GL-stage models are defined. These two classes of logical models are logic programming counterparts of the notion of range which is an established concept in argumentation semantics.
Tasks
Published	2016-02-29
URL	http://arxiv.org/abs/1602.08903v1
PDF	http://arxiv.org/pdf/1602.08903v1.pdf
PWC	https://paperswithcode.com/paper/range-based-argumentation-semantics-as-2
Repo
Framework

Adaptability of Neural Networks on Varying Granularity IR Tasks


Title	Adaptability of Neural Networks on Varying Granularity IR Tasks
Authors	Daniel Cohen, Qingyao Ai, W. Bruce Croft
Abstract	Recent work in Information Retrieval (IR) using Deep Learning models has yielded state of the art results on a variety of IR tasks. Deep neural networks (DNN) are capable of learning ideal representations of data during the training process, removing the need for independently extracting features. However, the structures of these DNNs are often tailored to perform on specific datasets. In addition, IR tasks deal with text at varying levels of granularity from single factoids to documents containing thousands of words. In this paper, we examine the role of the granularity on the performance of common state of the art DNN structures in IR.
Tasks	Information Retrieval
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07565v1
PDF	http://arxiv.org/pdf/1606.07565v1.pdf
PWC	https://paperswithcode.com/paper/adaptability-of-neural-networks-on-varying
Repo
Framework

$f$-Divergence Inequalities via Functional Domination


Title	$f$-Divergence Inequalities via Functional Domination
Authors	Igal Sason, Sergio Verdú
Abstract	This paper considers derivation of $f$-divergence inequalities via the approach of functional domination. Bounds on an $f$-divergence based on one or several other $f$-divergences are introduced, dealing with pairs of probability measures defined on arbitrary alphabets. In addition, a variety of bounds are shown to hold under boundedness assumptions on the relative information. The journal paper, which includes more approaches for the derivation of f-divergence inequalities and proofs, is available on the arXiv at https://arxiv.org/abs/1508.00335, and it has been published in the IEEE Trans. on Information Theory, vol. 62, no. 11, pp. 5973-6006, November 2016.
Tasks
Published	2016-10-28
URL	http://arxiv.org/abs/1610.09110v1
PDF	http://arxiv.org/pdf/1610.09110v1.pdf
PWC	https://paperswithcode.com/paper/f-divergence-inequalities-via-functional
Repo
Framework

Tool and Phase recognition using contextual CNN features


Title	Tool and Phase recognition using contextual CNN features
Authors	Manish Sahu, Anirban Mukhopadhyay, Angelika Szengel, Stefan Zachow
Abstract	A transfer learning method for generating features suitable for surgical tools and phase recognition from the ImageNet classification features [1] is proposed here. In addition, methods are developed for generating contextual features and combining them with time series analysis for final classification using multi-class random forest. The proposed pipeline is tested over the training and testing datasets of M2CAI16 challenges: tool and phase detection. Encouraging results are obtained by leave-one-out cross validation evaluation on the training dataset.
Tasks	Time Series, Time Series Analysis, Transfer Learning
Published	2016-10-27
URL	http://arxiv.org/abs/1610.08854v1
PDF	http://arxiv.org/pdf/1610.08854v1.pdf
PWC	https://paperswithcode.com/paper/tool-and-phase-recognition-using-contextual
Repo
Framework

Implementing a Relevance Tracker Module


Title	Implementing a Relevance Tracker Module
Authors	Joachim Jansen, Jo Devriendt, Bart Bogaerts, Gerda Janssens, Marc Denecker
Abstract	PC(ID) extends propositional logic with inductive definitions: rule sets under the well-founded semantics. Recently, a notion of relevance was introduced for this language. This notion determines the set of undecided literals that can still influence the satisfiability of a PC(ID) formula in a given partial assignment. The idea is that the PC(ID) solver can make decisions only on relevant literals without losing soundness and thus safely ignore irrelevant literals. One important insight that the relevance of a literal is completely determined by the current solver state. During search, the solver state changes have an effect on the relevance of literals. In this paper, we discuss an incremental, lightweight implementation of a relevance tracker module that can be added to and interact with an out-of-the-box SAT(ID) solver.
Tasks
Published	2016-08-19
URL	http://arxiv.org/abs/1608.05609v1
PDF	http://arxiv.org/pdf/1608.05609v1.pdf
PWC	https://paperswithcode.com/paper/implementing-a-relevance-tracker-module
Repo
Framework

A Probabilistic Optimum-Path Forest Classifier for Binary Classification Problems


Title	A Probabilistic Optimum-Path Forest Classifier for Binary Classification Problems
Authors	Silas E. N. Fernandes, Danillo R. Pereira, Caio C. O. Ramos, Andre N. Souza, Joao P. Papa
Abstract	Probabilistic-driven classification techniques extend the role of traditional approaches that output labels (usually integer numbers) only. Such techniques are more fruitful when dealing with problems where one is not interested in recognition/identification only, but also into monitoring the behavior of consumers and/or machines, for instance. Therefore, by means of probability estimates, one can take decisions to work better in a number of scenarios. In this paper, we propose a probabilistic-based Optimum Path Forest (OPF) classifier to handle with binary classification problems, and we show it can be more accurate than naive OPF in a number of datasets. In addition to being just more accurate or not, probabilistic OPF turns to be another useful tool to the scientific community.
Tasks
Published	2016-09-04
URL	http://arxiv.org/abs/1609.00878v1
PDF	http://arxiv.org/pdf/1609.00878v1.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-optimum-path-forest
Repo
Framework

An empirical study for Vietnamese dependency parsing


Title	An empirical study for Vietnamese dependency parsing
Authors	Dat Quoc Nguyen, Mark Dras, Mark Johnson
Abstract	This paper presents an empirical comparison of different dependency parsers for Vietnamese, which has some unusual characteristics such as copula drop and verb serialization. Experimental results show that the neural network-based parsers perform significantly better than the traditional parsers. We report the highest parsing scores published to date for Vietnamese with the labeled attachment score (LAS) at 73.53% and the unlabeled attachment score (UAS) at 80.66%.
Tasks	Dependency Parsing
Published	2016-11-03
URL	http://arxiv.org/abs/1611.00995v1
PDF	http://arxiv.org/pdf/1611.00995v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-study-for-vietnamese-dependency
Repo
Framework

Penta and Hexa Valued Representation of Neutrosophic Information


Title	Penta and Hexa Valued Representation of Neutrosophic Information
Authors	Vasile Patrascu
Abstract	Starting from the primary representation of neutrosophic information, namely the degree of truth, degree of indeterminacy and degree of falsity, we define a nuanced representation in a penta valued fuzzy space, described by the index of truth, index of falsity, index of ignorance, index of contradiction and index of hesitation. Also, it was constructed an associated penta valued logic and then using this logic, it was defined for the proposed penta valued structure the following operators: union, intersection, negation, complement and dual. Then, the penta valued representation is extended to a hexa valued one, adding the sixth component, namely the index of ambiguity.
Tasks
Published	2016-03-10
URL	http://arxiv.org/abs/1603.03729v1
PDF	http://arxiv.org/pdf/1603.03729v1.pdf
PWC	https://paperswithcode.com/paper/penta-and-hexa-valued-representation-of
Repo
Framework

An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates


Title	An ensemble of machine learning and anti-learning methods for predicting tumour patient survival rates
Authors	Christopher Roadknight, Durga Suryanarayanan, Uwe Aickelin, John Scholefield, Lindy Durrant
Abstract	This paper primarily addresses a dataset relating to cellular, chemical and physical conditions of patients gathered at the time they are operated upon to remove colorectal tumours. This data provides a unique insight into the biochemical and immunological status of patients at the point of tumour removal along with information about tumour classification and post-operative survival. The relationship between severity of tumour, based on TNM staging, and survival is still unclear for patients with TNM stage 2 and 3 tumours. We ask whether it is possible to predict survival rate more accurately using a selection of machine learning techniques applied to subsets of data to gain a deeper understanding of the relationships between a patient’s biochemical markers and survival. We use a range of feature selection and single classification techniques to predict the 5 year survival rate of TNM stage 2 and 3 patients which initially produces less than ideal results. The performance of each model individually is then compared with subsets of the data where agreement is reached for multiple models. This novel method of selective ensembling demonstrates that significant improvements in model accuracy on an unseen test set can be achieved for patients where agreement between models is achieved. Finally we point at a possible method to identify whether a patients prognosis can be accurately predicted or not.
Tasks	Feature Selection
Published	2016-07-21
URL	http://arxiv.org/abs/1607.06190v1
PDF	http://arxiv.org/pdf/1607.06190v1.pdf
PWC	https://paperswithcode.com/paper/an-ensemble-of-machine-learning-and-anti
Repo
Framework

Modelling Chemical Reasoning to Predict Reactions


Title	Modelling Chemical Reasoning to Predict Reactions
Authors	Marwin H. S. Segler, Mark P. Waller
Abstract	The ability to reason beyond established knowledge allows Organic Chemists to solve synthetic problems and to invent novel transformations. Here, we propose a model which mimics chemical reasoning and formalises reaction prediction as finding missing links in a knowledge graph. We have constructed a knowledge graph containing 14.4 million molecules and 8.2 million binary reactions, which represents the bulk of all chemical reactions ever published in the scientific literature. Our model outperforms a rule-based expert system in the reaction prediction task for 180,000 randomly selected binary reactions. We show that our data-driven model generalises even beyond known reaction types, and is thus capable of effectively (re-) discovering novel transformations (even including transition-metal catalysed reactions). Our model enables computers to infer hypotheses about reactivity and reactions by only considering the intrinsic local structure of the graph, and because each single reaction prediction is typically achieved in a sub-second time frame, our model can be used as a high-throughput generator of reaction hypotheses for reaction discovery.
Tasks
Published	2016-08-25
URL	http://arxiv.org/abs/1608.07117v1
PDF	http://arxiv.org/pdf/1608.07117v1.pdf
PWC	https://paperswithcode.com/paper/modelling-chemical-reasoning-to-predict
Repo
Framework

Joint Estimation of Precision Matrices in Heterogeneous Populations


Title	Joint Estimation of Precision Matrices in Heterogeneous Populations
Authors	Takumi Saegusa, Ali Shojaie
Abstract	We introduce a general framework for estimation of inverse covariance, or precision, matrices from heterogeneous populations. The proposed framework uses a Laplacian shrinkage penalty to encourage similarity among estimates from disparate, but related, subpopulations, while allowing for differences among matrices. We propose an efficient alternating direction method of multipliers (ADMM) algorithm for parameter estimation, as well as its extension for faster computation in high dimensions by thresholding the empirical covariance matrix to identify the joint block diagonal structure in the estimated precision matrices. We establish both variable selection and norm consistency of the proposed estimator for distributions with exponential or polynomial tails. Further, to extend the applicability of the method to the settings with unknown populations structure, we propose a Laplacian penalty based on hierarchical clustering, and discuss conditions under which this data-driven choice results in consistent estimation of precision matrices in heterogenous populations. Extensive numerical studies and applications to gene expression data from subtypes of cancer with distinct clinical outcomes indicate the potential advantages of the proposed method over existing approaches.
Tasks
Published	2016-01-02
URL	http://arxiv.org/abs/1601.00142v1
PDF	http://arxiv.org/pdf/1601.00142v1.pdf
PWC	https://paperswithcode.com/paper/joint-estimation-of-precision-matrices-in
Repo
Framework

The Optional Prisoner’s Dilemma in a Spatial Environment: Coevolving Game Strategy and Link Weights


Title	The Optional Prisoner’s Dilemma in a Spatial Environment: Coevolving Game Strategy and Link Weights
Authors	Marcos Cardinot, Colm O’Riordan, Josephine Griffith
Abstract	In this paper, the Optional Prisoner’s Dilemma game in a spatial environment, with coevolutionary rules for both the strategy and network links between agents, is studied. Using a Monte Carlo simulation approach, a number of experiments are performed to identify favourable configurations of the environment for the emergence of cooperation in adverse scenarios. Results show that abstainers play a key role in the protection of cooperators against exploitation from defectors. Scenarios of cyclic competition and of full dominance of cooperation are also observed. This work provides insights towards gaining an in-depth understanding of the emergence of cooperative behaviour in real-world systems.
Tasks
Published	2016-09-19
URL	http://arxiv.org/abs/1609.06560v1
PDF	http://arxiv.org/pdf/1609.06560v1.pdf
PWC	https://paperswithcode.com/paper/the-optional-prisoners-dilemma-in-a-spatial
Repo
Framework

Temporal Registration in In-Utero Volumetric MRI Time Series


Title	Temporal Registration in In-Utero Volumetric MRI Time Series
Authors	Ruizhi Liao, Esra Turk, Miaomiao Zhang, Jie Luo, Ellen Grant, Elfar Adalsteinsson, Polina Golland
Abstract	We present a robust method to correct for motion and deformations for in-utero volumetric MRI time series. Spatio-temporal analysis of dynamic MRI requires robust alignment across time in the presence of substantial and unpredictable motion. We make a Markov assumption on the nature of deformations to take advantage of the temporal structure in the image data. Forward message passing in the corresponding hidden Markov model (HMM) yields an estimation algorithm that only has to account for relatively small motion between consecutive frames. We demonstrate the utility of the temporal model by showing that its use improves the accuracy of the segmentation propagation through temporal registration. Our results suggest that the proposed model captures accurately the temporal dynamics of deformations in in-utero MRI time series.
Tasks	Time Series
Published	2016-08-12
URL	http://arxiv.org/abs/1608.03907v1
PDF	http://arxiv.org/pdf/1608.03907v1.pdf
PWC	https://paperswithcode.com/paper/temporal-registration-in-in-utero-volumetric
Repo
Framework

A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy


Title	A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy
Authors	Yanan Zhu, Qi Ouyang, Youdong Mao
Abstract	Background: Single-particle cryo-electron microscopy (cryo-EM) has become a popular tool for structural determination of biological macromolecular complexes. High-resolution cryo-EM reconstruction often requires hundreds of thousands of single-particle images. Particle extraction from experimental micrographs thus can be laborious and presents a major practical bottleneck in cryo-EM structural determination. Existing computational methods of particle picking often use low-resolution templates as inputs for particle matching, making it possible to cause reference-dependent bias. It is critical to develop a highly efficient template-free method to automatically recognize particle images from cryo-EM micrographs. Results: We developed a deep learning-based algorithmic framework, DeepEM, for single-particle recognition from noisy cryo-EM micrographs, enabling automated particle picking, selection and verification in an integrated fashion. The kernel of DeepEM is built upon a convolutional neural network (CNN) of eight layers, which can be recursively trained to be highly “knowledgeable”. Our approach exhibits improved performance and high precision when tested on the standard KLH dataset. Application of DeepEM to several challenging experimental cryo-EM datasets demonstrates its capability in avoiding selection of un-wanted particles and non-particles even when true particles contain fewer features. Conclusions: The DeepEM method derived from a deep CNN allows automated particle extraction from raw cryo-EM micrographs in the absence of templates, which demonstrated improved performance, objectivity and accuracy. Application of this novel approach is expected to free the labor involved in single-particle verification, thus promoting the efficiency of cryo-EM data processing.
Tasks
Published	2016-05-18
URL	http://arxiv.org/abs/1605.05543v2
PDF	http://arxiv.org/pdf/1605.05543v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-convolutional-neural-network-approach
Repo
Framework

Simpler PAC-Bayesian Bounds for Hostile Data


Title	Simpler PAC-Bayesian Bounds for Hostile Data
Authors	Pierre Alquier, Benjamin Guedj
Abstract	PAC-Bayesian learning bounds are of the utmost interest to the learning community. Their role is to connect the generalization ability of an aggregation distribution $\rho$ to its empirical risk and to its Kullback-Leibler divergence with respect to some prior distribution $\pi$. Unfortunately, most of the available bounds typically rely on heavy assumptions such as boundedness and independence of the observations. This paper aims at relaxing these constraints and provides PAC-Bayesian learning bounds that hold for dependent, heavy-tailed observations (hereafter referred to as \emph{hostile data}). In these bounds the Kullack-Leibler divergence is replaced with a general version of Csisz'ar’s $f$-divergence. We prove a general PAC-Bayesian bound, and show how to use it in various hostile settings.
Tasks
Published	2016-10-23
URL	https://arxiv.org/abs/1610.07193v2
PDF	https://arxiv.org/pdf/1610.07193v2.pdf
PWC	https://paperswithcode.com/paper/simpler-pac-bayesian-bounds-for-hostile-data
Repo
Framework