Paper Group ANR 140
Optimized Kernel Entropy Components. An extended MABAC for multi-attribute decision making using trapezoidal interval type-2 fuzzy numbers. Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering. Is a good offensive always the best defense?. Good Practice in CNN Feature Transfer. A Hierarchical Emotion Regul …
Optimized Kernel Entropy Components
| Title | Optimized Kernel Entropy Components |
| Authors | Emma Izquierdo-Verdiguier, Valero Laparra, Robert Jenssen, Luis Gómez-Chova, Gustau Camps-Valls |
| Abstract | This work addresses two main issues of the standard Kernel Entropy Component Analysis (KECA) algorithm: the optimization of the kernel decomposition and the optimization of the Gaussian kernel parameter. KECA roughly reduces to a sorting of the importance of kernel eigenvectors by entropy instead of by variance as in Kernel Principal Components Analysis. In this work, we propose an extension of the KECA method, named Optimized KECA (OKECA), that directly extracts the optimal features retaining most of the data entropy by means of compacting the information in very few features (often in just one or two). The proposed method produces features which have higher expressive power. In particular, it is based on the Independent Component Analysis (ICA) framework, and introduces an extra rotation to the eigen-decomposition, which is optimized via gradient ascent search. This maximum entropy preservation suggests that OKECA features are more efficient than KECA features for density estimation. In addition, a critical issue in both methods is the selection of the kernel parameter since it critically affects the resulting performance. Here we analyze the most common kernel length-scale selection criteria. Results of both methods are illustrated in different synthetic and real problems. Results show that 1) OKECA returns projections with more expressive power than KECA, 2) the most successful rule for estimating the kernel parameter is based on maximum likelihood, and 3) OKECA is more robust to the selection of the length-scale parameter in kernel density estimation. |
| Tasks | Density Estimation |
| Published | 2016-03-09 |
| URL | http://arxiv.org/abs/1603.02806v1 |
| http://arxiv.org/pdf/1603.02806v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimized-kernel-entropy-components |
| Repo | |
| Framework | |
An extended MABAC for multi-attribute decision making using trapezoidal interval type-2 fuzzy numbers
| Title | An extended MABAC for multi-attribute decision making using trapezoidal interval type-2 fuzzy numbers |
| Authors | Jagannath Roy, Ananta Ranjan, Animesh Debnath, Samarjit Kar |
| Abstract | In this paper, we attempt to extend Multi Attributive Border Approximation area Comparison (MABAC) approach for multi-attribute decision making (MADM) problems based on type-2 fuzzy sets (IT2FSs). As a special case of IT2FSs interval type-2 trapezoidal fuzzy numbers (IT2TrFNs) are adopted here to deal with uncertainties present in many practical evaluation and selection problems. A systematic description of MABAC based on IT2TrFNs is presented in the current study. The validity and feasibility of the proposed method are illustrated by a practical example of selecting the most suitable candidate for a software company which is heading to hire a system analysis engineer based on few attributes. Finally, a comparison with two other existing MADM methods is described. |
| Tasks | Decision Making |
| Published | 2016-07-05 |
| URL | http://arxiv.org/abs/1607.01254v4 |
| http://arxiv.org/pdf/1607.01254v4.pdf | |
| PWC | https://paperswithcode.com/paper/an-extended-mabac-for-multi-attribute |
| Repo | |
| Framework | |
Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering
| Title | Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering |
| Authors | Liwen Zhang, John Winn, Ryota Tomioka |
| Abstract | We propose the Gaussian attention model for content-based neural memory access. With the proposed attention model, a neural network has the additional degree of freedom to control the focus of its attention from a laser sharp attention to a broad attention. It is applicable whenever we can assume that the distance in the latent space reflects some notion of semantics. We use the proposed attention model as a scoring function for the embedding of a knowledge base into a continuous vector space and then train a model that performs question answering about the entities in the knowledge base. The proposed attention model can handle both the propagation of uncertainty when following a series of relations and also the conjunction of conditions in a natural way. On a dataset of soccer players who participated in the FIFA World Cup 2014, we demonstrate that our model can handle both path queries and conjunctive queries well. |
| Tasks | Question Answering |
| Published | 2016-11-07 |
| URL | http://arxiv.org/abs/1611.02266v2 |
| http://arxiv.org/pdf/1611.02266v2.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-attention-model-and-its-application |
| Repo | |
| Framework | |
Is a good offensive always the best defense?
| Title | Is a good offensive always the best defense? |
| Authors | J. Quetzalcóatl Toledo-Marín, Rogelio Díaz-Méndez, Marcelo del Castillo Mussot |
| Abstract | A checkers-like model game with a simplified set of rules is studied through extensive simulations of agents with different expertise and strategies. The introduction of complementary strategies, in a quite general way, provides a tool to mimic the basic ingredients of a wide scope of real games. We find that only for the player having the higher offensive expertise (the dominant player ), maximizing the offensive always increases the probability to win. For the non-dominant player, interestingly, a complete minimization of the offensive becomes the best way to win in many situations, depending on the relative values of the defense expertise. Further simulations on the interplay of defense expertise were done separately, in the context of a fully-offensive scenario, offering a starting point for analytical treatments. In particular, we established that in this scenario the total number of moves is defined only by the player with the lower defensive expertise. We believe that these results stand for a first step towards a new way to improve decisions-making in a large number of zero-sum real games. |
| Tasks | |
| Published | 2016-08-23 |
| URL | http://arxiv.org/abs/1608.07223v1 |
| http://arxiv.org/pdf/1608.07223v1.pdf | |
| PWC | https://paperswithcode.com/paper/is-a-good-offensive-always-the-best-defense |
| Repo | |
| Framework | |
Good Practice in CNN Feature Transfer
| Title | Good Practice in CNN Feature Transfer |
| Authors | Liang Zheng, Yali Zhao, Shengjin Wang, Jingdong Wang, Qi Tian |
| Abstract | The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification. Systematically, we study three facts in CNN transfer. 1) We demonstrate the advantage of using images with a properly large size as input to CNN instead of the conventionally resized one. 2) We benchmark the performance of different CNN layers improved by average/max pooling on the feature maps. Our observation suggests that the Conv5 feature yields very competitive accuracy under such pooling step. 3) We find that the simple combination of pooled features extracted across various CNN layers is effective in collecting evidences from both low and high level descriptors. Following these good practices, we are capable of improving the state of the art on a number of benchmarks to a large margin. |
| Tasks | Image Retrieval |
| Published | 2016-04-01 |
| URL | http://arxiv.org/abs/1604.00133v1 |
| http://arxiv.org/pdf/1604.00133v1.pdf | |
| PWC | https://paperswithcode.com/paper/good-practice-in-cnn-feature-transfer |
| Repo | |
| Framework | |
A Hierarchical Emotion Regulated Sensorimotor Model: Case Studies
| Title | A Hierarchical Emotion Regulated Sensorimotor Model: Case Studies |
| Authors | Junpei Zhong, Rony Novianto, Mingjun Dai, Xinzheng Zhang, Angelo Cangelosi |
| Abstract | Inspired by the hierarchical cognitive architecture and the perception-action model (PAM), we propose that the internal status acts as a kind of common-coding representation which affects, mediates and even regulates the sensorimotor behaviours. These regulation can be depicted in the Bayesian framework, that is why cognitive agents are able to generate behaviours with subtle differences according to their emotion or recognize the emotion by perception. A novel recurrent neural network called recurrent neural network with parametric bias units (RNNPB) runs in three modes, constructing a two-level emotion regulated learning model, was further applied to testify this theory in two different cases. |
| Tasks | |
| Published | 2016-05-11 |
| URL | http://arxiv.org/abs/1605.03269v1 |
| http://arxiv.org/pdf/1605.03269v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hierarchical-emotion-regulated-sensorimotor |
| Repo | |
| Framework | |
Aligning Packed Dependency Trees: a theory of composition for distributional semantics
| Title | Aligning Packed Dependency Trees: a theory of composition for distributional semantics |
| Authors | David Weir, Julie Weeds, Jeremy Reffin, Thomas Kober |
| Abstract | We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We show that these structures have the potential to capture the full sentential contexts of a lexeme and provide a uniform basis for the composition of distributional knowledge in a way that captures both mutual disambiguation and generalization. |
| Tasks | |
| Published | 2016-08-25 |
| URL | http://arxiv.org/abs/1608.07115v1 |
| http://arxiv.org/pdf/1608.07115v1.pdf | |
| PWC | https://paperswithcode.com/paper/aligning-packed-dependency-trees-a-theory-of |
| Repo | |
| Framework | |
Efficiency and Sequenceability in Fair Division of Indivisible Goods with Additive Preferences
| Title | Efficiency and Sequenceability in Fair Division of Indivisible Goods with Additive Preferences |
| Authors | Sylvain Bouveret, Michel Lemaître |
| Abstract | In fair division of indivisible goods, using sequences of sincere choices (or picking sequences) is a natural way to allocate the objects. The idea is the following: at each stage, a designated agent picks one object among those that remain. This paper, restricted to the case where the agents have numerical additive preferences over objects, revisits to some extent the seminal paper by Brams and King [9] which was specific to ordinal and linear order preferences over items. We point out similarities and differences with this latter context. In particular, we show that any Pareto-optimal allocation (under additive preferences) is sequenceable, but that the converse is not true anymore. This asymmetry leads naturally to the definition of a “scale of efficiency” having three steps: Pareto-optimality, sequenceability without Pareto-optimality, and non-sequenceability. Finally, we investigate the links between these efficiency properties and the “scale of fairness” we have described in an earlier work [7]: we first show that an allocation can be envy-free and non-sequenceable, but that every competitive equilibrium with equal incomes is sequenceable. Then we experimentally explore the links between the scales of efficiency and fairness. |
| Tasks | |
| Published | 2016-04-06 |
| URL | http://arxiv.org/abs/1604.01734v1 |
| http://arxiv.org/pdf/1604.01734v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficiency-and-sequenceability-in-fair |
| Repo | |
| Framework | |
Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
| Title | Unsupervised domain adaptation in brain lesion segmentation with adversarial networks |
| Authors | Konstantinos Kamnitsas, Christian Baumgartner, Christian Ledig, Virginia F. J. Newcombe, Joanna P. Simpson, Andrew D. Kane, David K. Menon, Aditya Nori, Antonio Criminisi, Daniel Rueckert, Ben Glocker |
| Abstract | Significant advances have been made towards building accurate automatic segmentation systems for a variety of biomedical applications using machine learning. However, the performance of these systems often degrades when they are applied on new data that differ from the training data, for example, due to variations in imaging protocols. Manually annotating new data for each test domain is not a feasible solution. In this work we investigate unsupervised domain adaptation using adversarial neural networks to train a segmentation method which is more invariant to differences in the input data, and which does not require any annotations on the test domain. Specifically, we learn domain-invariant features by learning to counter an adversarial network, which attempts to classify the domain of the input data by observing the activations of the segmentation network. Furthermore, we propose a multi-connected domain discriminator for improved adversarial training. Our system is evaluated using two MR databases of subjects with traumatic brain injuries, acquired using different scanners and imaging protocols. Using our unsupervised approach, we obtain segmentation accuracies which are close to the upper bound of supervised domain adaptation. |
| Tasks | Domain Adaptation, Lesion Segmentation, Unsupervised Domain Adaptation |
| Published | 2016-12-28 |
| URL | http://arxiv.org/abs/1612.08894v1 |
| http://arxiv.org/pdf/1612.08894v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-in-brain |
| Repo | |
| Framework | |
An active efficient coding model of the optokinetic nystagmus
| Title | An active efficient coding model of the optokinetic nystagmus |
| Authors | Chong Zhang, Jochen Triesch, Bertram E. Shi |
| Abstract | Optokinetic nystagmus (OKN) is an involuntary eye movement responsible for stabilizing retinal images in the presence of relative motion between an observer and the environment. Fully understanding the development of optokinetic nystagmus requires a neurally plausible computational model that accounts for the neural development and the behavior. To date, work in this area has been limited. We propose a neurally plausible framework for the joint development of disparity and motion tuning in the visual cortex, the optokinetic and vergence eye movements. This framework models the joint emergence of both perception and behavior, and accounts for the importance of the development of normal vergence control and binocular vision in achieving normal monocular OKN (mOKN) behaviors. Because the model includes behavior, we can simulate the same perturbations as performed in past experiments, such as artificially induced strabismus. The proposed model agrees both qualitatively and quantitatively with a number of findings from the literature on both binocular vision as well as the optokinetic reflex. Finally, our model also makes quantitative predictions about the OKN behavior using the same methods used to characterize the OKN in the experimental literature. |
| Tasks | |
| Published | 2016-06-21 |
| URL | http://arxiv.org/abs/1606.06443v3 |
| http://arxiv.org/pdf/1606.06443v3.pdf | |
| PWC | https://paperswithcode.com/paper/an-active-efficient-coding-model-of-the |
| Repo | |
| Framework | |
3D Human Pose Estimation = 2D Pose Estimation + Matching
| Title | 3D Human Pose Estimation = 2D Pose Estimation + Matching |
| Authors | Ching-Hang Chen, Deva Ramanan |
| Abstract | We explore 3D human pose estimation from a single RGB image. While many approaches try to directly predict 3D pose from image measurements, we explore a simple architecture that reasons through intermediate 2D pose predictions. Our approach is based on two key observations (1) Deep neural nets have revolutionized 2D pose estimation, producing accurate 2D predictions even for poses with self occlusions. (2) Big-data sets of 3D mocap data are now readily available, making it tempting to lift predicted 2D poses to 3D through simple memorization (e.g., nearest neighbors). The resulting architecture is trivial to implement with off-the-shelf 2D pose estimation systems and 3D mocap libraries. Importantly, we demonstrate that such methods outperform almost all state-of-the-art 3D pose estimation systems, most of which directly try to regress 3D pose from 2D measurements. |
| Tasks | 3D Human Pose Estimation, 3D Pose Estimation, Pose Estimation |
| Published | 2016-12-20 |
| URL | http://arxiv.org/abs/1612.06524v2 |
| http://arxiv.org/pdf/1612.06524v2.pdf | |
| PWC | https://paperswithcode.com/paper/3d-human-pose-estimation-2d-pose-estimation |
| Repo | |
| Framework | |
Learning Deep Architectures for Interaction Prediction in Structure-based Virtual Screening
| Title | Learning Deep Architectures for Interaction Prediction in Structure-based Virtual Screening |
| Authors | Adam Gonczarek, Jakub M. Tomczak, Szymon Zaręba, Joanna Kaczmar, Piotr Dąbrowski, Michał J. Walczak |
| Abstract | We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each compound separately. These fingerprints are further transformed non-linearly, their inner-product is calculated and used to predict the binding potential. Moreover, we show that widely used benchmark datasets may be insufficient for testing structure-based virtual screening methods that utilize machine learning. Therefore, we introduce a new benchmark dataset, which we constructed based on DUD-E and PDBBind databases. |
| Tasks | |
| Published | 2016-10-23 |
| URL | http://arxiv.org/abs/1610.07187v3 |
| http://arxiv.org/pdf/1610.07187v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deep-architectures-for-interaction |
| Repo | |
| Framework | |
The IBM 2016 Speaker Recognition System
| Title | The IBM 2016 Speaker Recognition System |
| Authors | Seyed Omid Sadjadi, Sriram Ganapathy, Jason W. Pelecanos |
| Abstract | In this paper we describe the recent advancements made in the IBM i-vector speaker recognition system for conversational speech. In particular, we identify key techniques that contribute to significant improvements in performance of our system, and quantify their contributions. The techniques include: 1) a nearest-neighbor discriminant analysis (NDA) approach that is formulated to alleviate some of the limitations associated with the conventional linear discriminant analysis (LDA) that assumes Gaussian class-conditional distributions, 2) the application of speaker- and channel-adapted features, which are derived from an automatic speech recognition (ASR) system, for speaker recognition, and 3) the use of a deep neural network (DNN) acoustic model with a large number of output units (~10k senones) to compute the frame-level soft alignments required in the i-vector estimation process. We evaluate these techniques on the NIST 2010 speaker recognition evaluation (SRE) extended core conditions involving telephone and microphone trials. Experimental results indicate that: 1) the NDA is more effective (up to 35% relative improvement in terms of EER) than the traditional parametric LDA for speaker recognition, 2) when compared to raw acoustic features (e.g., MFCCs), the ASR speaker-adapted features provide gains in speaker recognition performance, and 3) increasing the number of output units in the DNN acoustic model (i.e., increasing the senone set size from 2k to 10k) provides consistent improvements in performance (for example from 37% to 57% relative EER gains over our baseline GMM i-vector system). To our knowledge, results reported in this paper represent the best performances published to date on the NIST SRE 2010 extended core tasks. |
| Tasks | Speaker Recognition, Speech Recognition |
| Published | 2016-02-23 |
| URL | http://arxiv.org/abs/1602.07291v1 |
| http://arxiv.org/pdf/1602.07291v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-ibm-2016-speaker-recognition-system |
| Repo | |
| Framework | |
NewsQA: A Machine Comprehension Dataset
| Title | NewsQA: A Machine Comprehension Dataset |
| Authors | Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, Kaheer Suleman |
| Abstract | We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text from the corresponding articles. We collect this dataset through a four-stage process designed to solicit exploratory questions that require reasoning. A thorough analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment. We measure human performance on the dataset and compare it to several strong neural models. The performance gap between humans and machines (0.198 in F1) indicates that significant progress can be made on NewsQA through future research. The dataset is freely available at https://datasets.maluuba.com/NewsQA. |
| Tasks | Natural Language Inference, Reading Comprehension |
| Published | 2016-11-29 |
| URL | http://arxiv.org/abs/1611.09830v3 |
| http://arxiv.org/pdf/1611.09830v3.pdf | |
| PWC | https://paperswithcode.com/paper/newsqa-a-machine-comprehension-dataset |
| Repo | |
| Framework | |
On the Pitfalls of Nested Monte Carlo
| Title | On the Pitfalls of Nested Monte Carlo |
| Authors | Tom Rainforth, Robert Cornish, Hongseok Yang, Frank Wood |
| Abstract | There is an increasing interest in estimating expectations outside of the classical inference framework, such as for models expressed as probabilistic programs. Many of these contexts call for some form of nested inference to be applied. In this paper, we analyse the behaviour of nested Monte Carlo (NMC) schemes, for which classical convergence proofs are insufficient. We give conditions under which NMC will converge, establish a rate of convergence, and provide empirical data that suggests that this rate is observable in practice. Finally, we prove that general-purpose nested inference schemes are inherently biased. Our results serve to warn of the dangers associated with naive composition of inference and models. |
| Tasks | |
| Published | 2016-12-03 |
| URL | http://arxiv.org/abs/1612.00951v1 |
| http://arxiv.org/pdf/1612.00951v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-pitfalls-of-nested-monte-carlo |
| Repo | |
| Framework | |
