May 6, 2019

2623 words 13 mins read

Paper Group ANR 403

Seer: Empowering Software Defined Networking with Data Analytics. Resolving Out-of-Vocabulary Words with Bilingual Embeddings in Machine Translation. Deep Retinal Image Understanding. Online Open World Recognition. Statistical comparison of classifiers through Bayesian hierarchical modelling. Improving Information Extraction by Acquiring External E …

Seer: Empowering Software Defined Networking with Data Analytics


Title	Seer: Empowering Software Defined Networking with Data Analytics
Authors	Kyriakos Sideris, Reza Nejabati, Dimitra Simeonidou
Abstract	Network complexity is increasing, making network control and orchestration a challenging task. The proliferation of network information and tools for data analytics can provide an important insight into resource provisioning and optimisation. The network knowledge incorporated in software defined networking can facilitate the knowledge driven control, leveraging the network programmability. We present Seer: a flexible, highly configurable data analytics platform for network intelligence based on software defined networking and big data principles. Seer combines a computational engine with a distributed messaging system to provide a scalable, fault tolerant and real-time platform for knowledge extraction. Our first prototype uses Apache Spark for streaming analytics and open network operating system (ONOS) controller to program a network in real-time. The first application we developed aims to predict the mobility pattern of mobile devices inside a smart city environment.
Tasks
Published	2016-10-04
URL	http://arxiv.org/abs/1610.01221v1
PDF	http://arxiv.org/pdf/1610.01221v1.pdf
PWC	https://paperswithcode.com/paper/seer-empowering-software-defined-networking
Repo
Framework

Resolving Out-of-Vocabulary Words with Bilingual Embeddings in Machine Translation


Title	Resolving Out-of-Vocabulary Words with Bilingual Embeddings in Machine Translation
Authors	Pranava Swaroop Madhyastha, Cristina España-Bonet
Abstract	Out-of-vocabulary words account for a large proportion of errors in machine translation systems, especially when the system is used on a different domain than the one where it was trained. In order to alleviate the problem, we propose to use a log-bilinear softmax-based model for vocabulary expansion, such that given an out-of-vocabulary source word, the model generates a probabilistic list of possible translations in the target language. Our model uses only word embeddings trained on significantly large unlabelled monolingual corpora and trains over a fairly small, word-to-word bilingual dictionary. We input this probabilistic list into a standard phrase-based statistical machine translation system and obtain consistent improvements in translation quality on the English-Spanish language pair. Especially, we get an improvement of 3.9 BLEU points when tested over an out-of-domain test set.
Tasks	Machine Translation, Word Embeddings
Published	2016-08-05
URL	http://arxiv.org/abs/1608.01910v1
PDF	http://arxiv.org/pdf/1608.01910v1.pdf
PWC	https://paperswithcode.com/paper/resolving-out-of-vocabulary-words-with
Repo
Framework

Deep Retinal Image Understanding


Title	Deep Retinal Image Understanding
Authors	Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc Van Gool
Abstract	This paper presents Deep Retinal Image Understanding (DRIU), a unified framework of retinal image analysis that provides both retinal vessel and optic disc segmentation. We make use of deep Convolutional Neural Networks (CNNs), which have proven revolutionary in other fields of computer vision such as object detection and image classification, and we bring their power to the study of eye fundus images. DRIU uses a base network architecture on which two set of specialized layers are trained to solve both the retinal vessel and optic disc segmentation. We present experimental validation, both qualitative and quantitative, in four public datasets for these tasks. In all of them, DRIU presents super-human performance, that is, it shows results more consistent with a gold standard than a second human annotator used as control.
Tasks	Image Classification, Object Detection
Published	2016-09-05
URL	http://arxiv.org/abs/1609.01103v1
PDF	http://arxiv.org/pdf/1609.01103v1.pdf
PWC	https://paperswithcode.com/paper/deep-retinal-image-understanding
Repo
Framework

Online Open World Recognition


Title	Online Open World Recognition
Authors	Rocco De Rosa, Thomas Mensink, Barbara Caputo
Abstract	As we enter into the big data age and an avalanche of images have become readily available, recognition systems face the need to move from close, lab settings where the number of classes and training data are fixed, to dynamic scenarios where the number of categories to be recognized grows continuously over time, as well as new data providing useful information to update the system. Recent attempts, like the open world recognition framework, tried to inject dynamics into the system by detecting new unknown classes and adding them incrementally, while at the same time continuously updating the models for the known classes. incrementally adding new classes and detecting instances from unknown classes, while at the same time continuously updating the models for the known classes. In this paper we argue that to properly capture the intrinsic dynamic of open world recognition, it is necessary to add to these aspects (a) the incremental learning of the underlying metric, (b) the incremental estimate of confidence thresholds for the unknown classes, and (c) the use of local learning to precisely describe the space of classes. We extend three existing metric learning algorithms towards these goals by using online metric learning. Experimentally we validate our approach on two large-scale datasets in different learning scenarios. For all these scenarios our proposed methods outperform their non-online counterparts. We conclude that local and online learning is important to capture the full dynamics of open world recognition.
Tasks	Metric Learning
Published	2016-04-08
URL	http://arxiv.org/abs/1604.02275v1
PDF	http://arxiv.org/pdf/1604.02275v1.pdf
PWC	https://paperswithcode.com/paper/online-open-world-recognition
Repo
Framework

Statistical comparison of classifiers through Bayesian hierarchical modelling


Title	Statistical comparison of classifiers through Bayesian hierarchical modelling
Authors	Giorgio Corani, Alessio Benavoli, Janez Demšar, Francesca Mangili, Marco Zaffalon
Abstract	Usually one compares the accuracy of two competing classifiers via null hypothesis significance tests (nhst). Yet the nhst tests suffer from important shortcomings, which can be overcome by switching to Bayesian hypothesis testing. We propose a Bayesian hierarchical model which jointly analyzes the cross-validation results obtained by two classifiers on multiple data sets. It returns the posterior probability of the accuracies of the two classifiers being practically equivalent or significantly different. A further strength of the hierarchical model is that, by jointly analyzing the results obtained on all data sets, it reduces the estimation error compared to the usual approach of averaging the cross-validation results obtained on a given data set.
Tasks
Published	2016-09-28
URL	http://arxiv.org/abs/1609.08905v3
PDF	http://arxiv.org/pdf/1609.08905v3.pdf
PWC	https://paperswithcode.com/paper/statistical-comparison-of-classifiers-through
Repo
Framework

Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning


Title	Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
Authors	Karthik Narasimhan, Adam Yala, Regina Barzilay
Abstract	Most successful information extraction systems operate with access to a large collection of documents. In this work, we explore the task of acquiring and incorporating external evidence to improve extraction accuracy in domains where the amount of training data is scarce. This process entails issuing search queries, extraction from new sources and reconciliation of extracted values, which are repeated until sufficient evidence is collected. We approach the problem using a reinforcement learning framework where our model learns to select optimal actions based on contextual information. We employ a deep Q-network, trained to optimize a reward function that reflects extraction accuracy while penalizing extra effort. Our experiments on two databases – of shooting incidents, and food adulteration cases – demonstrate that our system significantly outperforms traditional extractors and a competitive meta-classifier baseline.
Tasks
Published	2016-03-25
URL	http://arxiv.org/abs/1603.07954v3
PDF	http://arxiv.org/pdf/1603.07954v3.pdf
PWC	https://paperswithcode.com/paper/improving-information-extraction-by-acquiring
Repo
Framework

Natural Language Generation enhances human decision-making with uncertain information


Title	Natural Language Generation enhances human decision-making with uncertain information
Authors	Dimitra Gkatzia, Oliver Lemon, Verena Rieser
Abstract	Decision-making is often dependent on uncertain data, e.g. data associated with confidence scores or probabilities. We present a comparison of different information presentations for uncertain data and, for the first time, measure their effects on human decision-making. We show that the use of Natural Language Generation (NLG) improves decision-making under uncertainty, compared to state-of-the-art graphical-based representation methods. In a task-based study with 442 adults, we found that presentations using NLG lead to 24% better decision-making on average than the graphical presentations, and to 44% better decision-making when NLG is combined with graphics. We also show that women achieve significantly better results when presented with NLG output (an 87% increase on average compared to graphical presentations).
Tasks	Decision Making, Decision Making Under Uncertainty, Text Generation
Published	2016-06-10
URL	http://arxiv.org/abs/1606.03254v2
PDF	http://arxiv.org/pdf/1606.03254v2.pdf
PWC	https://paperswithcode.com/paper/natural-language-generation-enhances-human
Repo
Framework

Testing for Causality in Continuous Time Bayesian Network Models of High-Frequency Data


Title	Testing for Causality in Continuous Time Bayesian Network Models of High-Frequency Data
Authors	Jonas Hallgren, Timo Koski
Abstract	Continuous time Bayesian networks are investigated with a special focus on their ability to express causality. A framework is presented for doing inference in these networks. The central contributions are a representation of the intensity matrices for the networks and the introduction of a causality measure. A new model for high-frequency financial data is presented. It is calibrated to market data and by the new causality measure it performs better than older models.
Tasks
Published	2016-01-25
URL	http://arxiv.org/abs/1601.06651v1
PDF	http://arxiv.org/pdf/1601.06651v1.pdf
PWC	https://paperswithcode.com/paper/testing-for-causality-in-continuous-time
Repo
Framework

Q-Learning with Basic Emotions


Title	Q-Learning with Basic Emotions
Authors	Wilfredo Badoy Jr., Kardi Teknomo
Abstract	Q-learning is a simple and powerful tool in solving dynamic problems where environments are unknown. It uses a balance of exploration and exploitation to find an optimal solution to the problem. In this paper, we propose using four basic emotions: joy, sadness, fear, and anger to influence a Qlearning agent. Simulations show that the proposed affective agent requires lesser number of steps to find the optimal path. We found when affective agent finds the optimal path, the ratio between exploration to exploitation gradually decreases, indicating lower total step count in the long run
Tasks	Q-Learning
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01468v1
PDF	http://arxiv.org/pdf/1609.01468v1.pdf
PWC	https://paperswithcode.com/paper/q-learning-with-basic-emotions
Repo
Framework

An image compression and encryption scheme based on deep learning


Title	An image compression and encryption scheme based on deep learning
Authors	Fei Hu, Changjiu Pu, Haowei Gao, Mengzi Tang, Li Li
Abstract	Stacked Auto-Encoder (SAE) is a kind of deep learning algorithm for unsupervised learning. Which has multi layers that project the vector representation of input data into a lower vector space. These projection vectors are dense representations of the input data. As a result, SAE can be used for image compression. Using chaotic logistic map, the compression ones can further be encrypted. In this study, an application of image compression and encryption is suggested using SAE and chaotic logistic map. Experiments show that this application is feasible and effective. It can be used for image transmission and image protection on internet simultaneously.
Tasks	Image Compression
Published	2016-08-16
URL	http://arxiv.org/abs/1608.05001v2
PDF	http://arxiv.org/pdf/1608.05001v2.pdf
PWC	https://paperswithcode.com/paper/an-image-compression-and-encryption-scheme
Repo
Framework

Structure in the Value Function of Two-Player Zero-Sum Games of Incomplete Information


Title	Structure in the Value Function of Two-Player Zero-Sum Games of Incomplete Information
Authors	Auke J. Wiggers, Frans A. Oliehoek, Diederik M. Roijers
Abstract	Zero-sum stochastic games provide a rich model for competitive decision making. However, under general forms of state uncertainty as considered in the Partially Observable Stochastic Game (POSG), such decision making problems are still not very well understood. This paper makes a contribution to the theory of zero-sum POSGs by characterizing structure in their value function. In particular, we introduce a new formulation of the value function for zs-POSGs as a function of the “plan-time sufficient statistics” (roughly speaking the information distribution in the POSG), which has the potential to enable generalization over such information distributions. We further delineate this generalization capability by proving a structural result on the shape of value function: it exhibits concavity and convexity with respect to appropriately chosen marginals of the statistic space. This result is a key pre-cursor for developing solution methods that may be able to exploit such structure. Finally, we show how these results allow us to reduce a zs-POSG to a “centralized” model with shared observations, thereby transferring results for the latter, narrower class, to games with individual (private) observations.
Tasks	Decision Making
Published	2016-06-22
URL	http://arxiv.org/abs/1606.06888v1
PDF	http://arxiv.org/pdf/1606.06888v1.pdf
PWC	https://paperswithcode.com/paper/structure-in-the-value-function-of-two-player
Repo
Framework

Improving Sparse Word Representations with Distributional Inference for Semantic Composition


Title	Improving Sparse Word Representations with Distributional Inference for Semantic Composition
Authors	Thomas Kober, Julie Weeds, Jeremy Reffin, David Weir
Abstract	Distributional models are derived from co-occurrences in a corpus, where only a small proportion of all possible plausible co-occurrences will be observed. This results in a very sparse vector space, requiring a mechanism for inferring missing knowledge. Most methods face this challenge in ways that render the resulting word representations uninterpretable, with the consequence that semantic composition becomes hard to model. In this paper we explore an alternative which involves explicitly inferring unobserved co-occurrences using the distributional neighbourhood. We show that distributional inference improves sparse word representations on several word similarity benchmarks and demonstrate that our model is competitive with the state-of-the-art for adjective-noun, noun-noun and verb-object compositions while being fully interpretable.
Tasks	Semantic Composition
Published	2016-08-24
URL	http://arxiv.org/abs/1608.06794v1
PDF	http://arxiv.org/pdf/1608.06794v1.pdf
PWC	https://paperswithcode.com/paper/improving-sparse-word-representations-with
Repo
Framework

(Bandit) Convex Optimization with Biased Noisy Gradient Oracles


Title	(Bandit) Convex Optimization with Biased Noisy Gradient Oracles
Authors	Xiaowei Hu, Prashanth L. A., András György, Csaba Szepesvári
Abstract	Algorithms for bandit convex optimization and online learning often rely on constructing noisy gradient estimates, which are then used in appropriately adjusted first-order algorithms, replacing actual gradients. Depending on the properties of the function to be optimized and the nature of “noise” in the bandit feedback, the bias and variance of gradient estimates exhibit various tradeoffs. In this paper we propose a novel framework that replaces the specific gradient estimation methods with an abstract oracle. With the help of the new framework we unify previous works, reproducing their results in a clean and concise fashion, while, perhaps more importantly, the framework also allows us to formally show that to achieve the optimal root-$n$ rate either the algorithms that use existing gradient estimators, or the proof techniques used to analyze them have to go beyond what exists today.
Tasks
Published	2016-09-22
URL	http://arxiv.org/abs/1609.07087v1
PDF	http://arxiv.org/pdf/1609.07087v1.pdf
PWC	https://paperswithcode.com/paper/bandit-convex-optimization-with-biased-noisy
Repo
Framework

Multi-Step Bayesian Optimization for One-Dimensional Feasibility Determination


Title	Multi-Step Bayesian Optimization for One-Dimensional Feasibility Determination
Authors	J. Massey Cashore, Lemuel Kumarga, Peter I. Frazier
Abstract	Bayesian optimization methods allocate limited sampling budgets to maximize expensive-to-evaluate functions. One-step-lookahead policies are often used, but computing optimal multi-step-lookahead policies remains a challenge. We consider a specialized Bayesian optimization problem: finding the superlevel set of an expensive one-dimensional function, with a Markov process prior. We compute the Bayes-optimal sampling policy efficiently, and characterize the suboptimality of one-step lookahead. Our numerical experiments demonstrate that the one-step lookahead policy is close to optimal in this problem, performing within 98% of optimal in the experimental settings considered.
Tasks
Published	2016-07-11
URL	http://arxiv.org/abs/1607.03195v1
PDF	http://arxiv.org/pdf/1607.03195v1.pdf
PWC	https://paperswithcode.com/paper/multi-step-bayesian-optimization-for-one
Repo
Framework

Multiplex lexical networks reveal patterns in early word acquisition in children


Title	Multiplex lexical networks reveal patterns in early word acquisition in children
Authors	Massimo Stella, Nicole M. Beckage, Markus Brede
Abstract	Network models of language have provided a way of linking cognitive processes to the structure and connectivity of language. However, one shortcoming of current approaches is focusing on only one type of linguistic relationship at a time, missing the complex multi-relational nature of language. In this work, we overcome this limitation by modelling the mental lexicon of English-speaking toddlers as a multiplex lexical network, i.e. a multi-layered network where N=529 words/nodes are connected according to four types of relationships: (i) free associations, (ii) feature sharing, (iii) co-occurrence, and (iv) phonological similarity. We provide analysis of the topology of the resulting multiplex and then proceed to evaluate single layers as well as the full multiplex structure on their ability to predict empirically observed age of acquisition data of English speaking toddlers. We find that the emerging multiplex network topology is an important proxy of the cognitive processes of acquisition, capable of capturing emergent lexicon structure. In fact, we show that the multiplex topology is fundamentally more powerful than individual layers in predicting the ordering with which words are acquired. Furthermore, multiplex analysis allows for a quantification of distinct phases of lexical acquisition in early learners: while initially all the multiplex layers contribute to word learning, after about month 23 free associations take the lead in driving word acquisition.
Tasks
Published	2016-09-11
URL	http://arxiv.org/abs/1609.03207v2
PDF	http://arxiv.org/pdf/1609.03207v2.pdf
PWC	https://paperswithcode.com/paper/multiplex-lexical-networks-reveal-patterns-in
Repo
Framework