May 6, 2019

2858 words 14 mins read

Paper Group ANR 243

Trading-off variance and complexity in stochastic gradient descent. BreakID: Static Symmetry Breaking for ASP (System Description). Mining Software Quality from Software Reviews: Research Trends and Open Issues. Automatic Detection of ADHD and ASD from Expressive Behaviour in RGBD Data. Improved generator objectives for GANs. Feature Engineering an …

Trading-off variance and complexity in stochastic gradient descent


Title	Trading-off variance and complexity in stochastic gradient descent
Authors	Vatsal Shah, Megasthenis Asteris, Anastasios Kyrillidis, Sujay Sanghavi
Abstract	Stochastic gradient descent is the method of choice for large-scale machine learning problems, by virtue of its light complexity per iteration. However, it lags behind its non-stochastic counterparts with respect to the convergence rate, due to high variance introduced by the stochastic updates. The popular Stochastic Variance-Reduced Gradient (SVRG) method mitigates this shortcoming, introducing a new update rule which requires infrequent passes over the entire input dataset to compute the full-gradient. In this work, we propose CheapSVRG, a stochastic variance-reduction optimization scheme. Our algorithm is similar to SVRG but instead of the full gradient, it uses a surrogate which can be efficiently computed on a small subset of the input data. It achieves a linear convergence rate —up to some error level, depending on the nature of the optimization problem—and features a trade-off between the computational complexity and the convergence rate. Empirical evaluation shows that CheapSVRG performs at least competitively compared to the state of the art.
Tasks
Published	2016-03-22
URL	http://arxiv.org/abs/1603.06861v1
PDF	http://arxiv.org/pdf/1603.06861v1.pdf
PWC	https://paperswithcode.com/paper/trading-off-variance-and-complexity-in
Repo
Framework

BreakID: Static Symmetry Breaking for ASP (System Description)


Title	BreakID: Static Symmetry Breaking for ASP (System Description)
Authors	Jo Devriendt, Bart Bogaerts
Abstract	Symmetry breaking has been proven to be an efficient preprocessing technique for satisfiability solving (SAT). In this paper, we port the state-of-the-art SAT symmetry breaker BreakID to answer set programming (ASP). The result is a lightweight tool that can be plugged in between the grounding and the solving phases that are common when modelling in ASP. We compare our tool with sbass, the current state-of-the-art symmetry breaker for ASP.
Tasks
Published	2016-08-30
URL	http://arxiv.org/abs/1608.08447v1
PDF	http://arxiv.org/pdf/1608.08447v1.pdf
PWC	https://paperswithcode.com/paper/breakid-static-symmetry-breaking-for-asp
Repo
Framework

Mining Software Quality from Software Reviews: Research Trends and Open Issues


Title	Mining Software Quality from Software Reviews: Research Trends and Open Issues
Authors	Issa Atoum, Ahmed Otoom
Abstract	Software review text fragments have considerably valuable information about users experience. It includes a huge set of properties including the software quality. Opinion mining or sentiment analysis is concerned with analyzing textual user judgments. The application of sentiment analysis on software reviews can find a quantitative value that represents software quality. Although many software quality methods are proposed they are considered difficult to customize and many of them are limited. This article investigates the application of opinion mining as an approach to extract software quality properties. We found that the major issues of software reviews mining using sentiment analysis are due to software lifecycle and the diverse users and teams.
Tasks	Opinion Mining, Sentiment Analysis
Published	2016-02-05
URL	http://arxiv.org/abs/1602.02133v1
PDF	http://arxiv.org/pdf/1602.02133v1.pdf
PWC	https://paperswithcode.com/paper/mining-software-quality-from-software-reviews
Repo
Framework

Automatic Detection of ADHD and ASD from Expressive Behaviour in RGBD Data


Title	Automatic Detection of ADHD and ASD from Expressive Behaviour in RGBD Data
Authors	Shashank Jaiswal, Michel Valstar, Alinda Gillott, David Daley
Abstract	Attention Deficit Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD) are neurodevelopmental conditions which impact on a significant number of children and adults. Currently, the diagnosis of such disorders is done by experts who employ standard questionnaires and look for certain behavioural markers through manual observation. Such methods for their diagnosis are not only subjective, difficult to repeat, and costly but also extremely time consuming. In this work, we present a novel methodology to aid diagnostic predictions about the presence/absence of ADHD and ASD by automatic visual analysis of a person’s behaviour. To do so, we conduct the questionnaires in a computer-mediated way while recording participants with modern RGBD (Colour+Depth) sensors. In contrast to previous automatic approaches which have focussed only detecting certain behavioural markers, our approach provides a fully automatic end-to-end system for directly predicting ADHD and ASD in adults. Using state of the art facial expression analysis based on Dynamic Deep Learning and 3D analysis of behaviour, we attain classification rates of 96% for Controls vs Condition (ADHD/ASD) group and 94% for Comorbid (ADHD+ASD) vs ASD only group. We show that our system is a potentially useful time saving contribution to the diagnostic field of ADHD and ASD.
Tasks
Published	2016-12-07
URL	http://arxiv.org/abs/1612.02374v1
PDF	http://arxiv.org/pdf/1612.02374v1.pdf
PWC	https://paperswithcode.com/paper/automatic-detection-of-adhd-and-asd-from
Repo
Framework

Improved generator objectives for GANs


Title	Improved generator objectives for GANs
Authors	Ben Poole, Alexander A. Alemi, Jascha Sohl-Dickstein, Anelia Angelova
Abstract	We present a framework to understand GAN training as alternating density ratio estimation and approximate divergence minimization. This provides an interpretation for the mismatched GAN generator and discriminator objectives often used in practice, and explains the problem of poor sample diversity. We also derive a family of generator objectives that target arbitrary $f$-divergences without minimizing a lower bound, and use them to train generative image models that target either improved sample quality or greater sample diversity.
Tasks
Published	2016-12-08
URL	http://arxiv.org/abs/1612.02780v1
PDF	http://arxiv.org/pdf/1612.02780v1.pdf
PWC	https://paperswithcode.com/paper/improved-generator-objectives-for-gans
Repo
Framework

Feature Engineering and Ensemble Modeling for Paper Acceptance Rank Prediction


Title	Feature Engineering and Ensemble Modeling for Paper Acceptance Rank Prediction
Authors	Yujie Qian, Yinpeng Dong, Ye Ma, Hailong Jin, Juanzi Li
Abstract	Measuring research impact and ranking academic achievement are important and challenging problems. Having an objective picture of research institution is particularly valuable for students, parents and funding agencies, and also attracts attention from government and industry. KDD Cup 2016 proposes the paper acceptance rank prediction task, in which the participants are asked to rank the importance of institutions based on predicting how many of their papers will be accepted at the 8 top conferences in computer science. In our work, we adopt a three-step feature engineering method, including basic features definition, finding similar conferences to enhance the feature set, and dimension reduction using PCA. We propose three ranking models and the ensemble methods for combining such models. Our experiment verifies the effectiveness of our approach. In KDD Cup 2016, we achieved the overall rank of the 2nd place.
Tasks	Dimensionality Reduction, Feature Engineering
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04369v1
PDF	http://arxiv.org/pdf/1611.04369v1.pdf
PWC	https://paperswithcode.com/paper/feature-engineering-and-ensemble-modeling-for
Repo
Framework

How do neurons operate on sparse distributed representations? A mathematical theory of sparsity, neurons and active dendrites


Title	How do neurons operate on sparse distributed representations? A mathematical theory of sparsity, neurons and active dendrites
Authors	Subutai Ahmad, Jeff Hawkins
Abstract	We propose a formal mathematical model for sparse representations and active dendrites in neocortex. Our model is inspired by recent experimental findings on active dendritic processing and NMDA spikes in pyramidal neurons. These experimental and modeling studies suggest that the basic unit of pattern memory in the neocortex is instantiated by small clusters of synapses operated on by localized non-linear dendritic processes. We derive a number of scaling laws that characterize the accuracy of such dendrites in detecting activation patterns in a neuronal population under adverse conditions. We introduce the union property which shows that synapses for multiple patterns can be randomly mixed together within a segment and still lead to highly accurate recognition. We describe simulation results that provide further insight into sparse representations as well as two primary results. First we show that pattern recognition by a neuron with active dendrites can be extremely accurate and robust with high dimensional sparse inputs even when using a tiny number of synapses to recognize large patterns. Second, equations representing recognition accuracy of a dendrite predict optimal NMDA spiking thresholds under a generous set of assumptions. The prediction tightly matches NMDA spiking thresholds measured in the literature. Our model matches many of the known properties of pyramidal neurons. As such the theory provides a mathematical framework for understanding the benefits and limits of sparse representations in cortical networks.
Tasks
Published	2016-01-05
URL	http://arxiv.org/abs/1601.00720v2
PDF	http://arxiv.org/pdf/1601.00720v2.pdf
PWC	https://paperswithcode.com/paper/how-do-neurons-operate-on-sparse-distributed
Repo
Framework

Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose


Title	Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose
Authors	Seyoung Park, Bruce Xiaohan Nie, Song-Chun Zhu
Abstract	This paper presents an attribute and-or grammar (A-AOG) model for jointly inferring human body pose and human attributes in a parse graph with attributes augmented to nodes in the hierarchical representation. In contrast to other popular methods in the current literature that train separate classifiers for poses and individual attributes, our method explicitly represents the decomposition and articulation of body parts, and account for the correlations between poses and attributes. The A-AOG model is an amalgamation of three traditional grammar formulations: (i) Phrase structure grammar representing the hierarchical decomposition of the human body from whole to parts; (ii) Dependency grammar modeling the geometric articulation by a kinematic graph of the body pose; and (iii) Attribute grammar accounting for the compatibility relations between different parts in the hierarchy so that their appearances follow a consistent style. The parse graph outputs human detection, pose estimation, and attribute prediction simultaneously, which are intuitive and interpretable. We conduct experiments on two tasks on two datasets, and experimental results demonstrate the advantage of joint modeling in comparison with computing poses and attributes independently. Furthermore, our model obtains better performance over existing methods for both pose estimation and attribute prediction tasks.
Tasks	Human Detection, Pose Estimation
Published	2016-05-06
URL	http://arxiv.org/abs/1605.02112v2
PDF	http://arxiv.org/pdf/1605.02112v2.pdf
PWC	https://paperswithcode.com/paper/attribute-and-or-grammar-for-joint-parsing-of
Repo
Framework

Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder


Title	Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder
Authors	Thanh-Le Ha, Jan Niehues, Alexander Waibel
Abstract	In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach. We are then able to employ attention-based NMT for many-to-many multilingual translation tasks. Our approach does not require any special treatment on the network architecture and it allows us to learn minimal number of free parameters in a standard way of training. Our approach has shown its effectiveness in an under-resourced translation scenario with considerable improvements up to 2.6 BLEU points. In addition, the approach has achieved interesting and promising results when applied in the translation task that there is no direct parallel corpus between source and target languages.
Tasks	Machine Translation
Published	2016-11-15
URL	http://arxiv.org/abs/1611.04798v1
PDF	http://arxiv.org/pdf/1611.04798v1.pdf
PWC	https://paperswithcode.com/paper/toward-multilingual-neural-machine
Repo
Framework

Easy-setup eye movement recording system for human-computer interaction


Title	Easy-setup eye movement recording system for human-computer interaction
Authors	Manh Duong Phung, Quang Vinh Tran, Kenji Hara, Hirohito Inagaki, Masanobu Abe
Abstract	Tracking the movement of human eyes is expected to yield natural and convenient applications based on human-computer interaction (HCI). To implement an effective eye-tracking system, eye movements must be recorded without placing any restriction on the user’s behavior or user discomfort. This paper describes an eye movement recording system that offers free-head, simple configuration. It does not require the user to wear anything on her head, and she can move her head freely. Instead of using a computer, the system uses a visual digital signal processor (DSP) camera to detect the position of eye corner, the center of pupil and then calculate the eye movement. Evaluation tests show that the sampling rate of the system can be 300 Hz and the accuracy is about 1.8 degree/s.
Tasks	Eye Tracking
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09427v1
PDF	http://arxiv.org/pdf/1611.09427v1.pdf
PWC	https://paperswithcode.com/paper/easy-setup-eye-movement-recording-system-for
Repo
Framework

Fusing Face and Periocular biometrics using Canonical correlation analysis


Title	Fusing Face and Periocular biometrics using Canonical correlation analysis
Authors	N. S. Lakshmiprabha
Abstract	This paper presents a novel face and periocular biometric fusion at feature level using canonical correlation analysis. Face recognition itself has limitations such as illumination, pose, expression, occlusion etc. Also, periocular biometrics has spectacles, head angle, hair and expression as its limitations. Unimodal biometrics cannot surmount all these limitations. The recognition accuracy can be increased by fusing dual information (face and periocular) from a single source (face image) using canonical correlation analysis (CCA). This work also proposes a new wavelet decomposed local binary pattern (WD-LBP) feature extractor which provides sufficient features for fusion. A detailed analysis on face and periocular biometrics shows that WD-LBP features are more accurate and faster than local binary pattern (LBP) and gabor wavelet. The experimental results using Muct face database reveals that the proposed multimodal biometrics performs better than the unimodal biometrics.
Tasks	Face Recognition
Published	2016-03-29
URL	http://arxiv.org/abs/1604.01683v1
PDF	http://arxiv.org/pdf/1604.01683v1.pdf
PWC	https://paperswithcode.com/paper/fusing-face-and-periocular-biometrics-using
Repo
Framework

Interpretable Deep Neural Networks for Single-Trial EEG Classification


Title	Interpretable Deep Neural Networks for Single-Trial EEG Classification
Authors	Irene Sturm, Sebastian Bach, Wojciech Samek, Klaus-Robert Müller
Abstract	Background: In cognitive neuroscience the potential of Deep Neural Networks (DNNs) for solving complex classification tasks is yet to be fully exploited. The most limiting factor is that DNNs as notorious ‘black boxes’ do not provide insight into neurophysiological phenomena underlying a decision. Layer-wise Relevance Propagation (LRP) has been introduced as a novel method to explain individual network decisions. New Method: We propose the application of DNNs with LRP for the first time for EEG data analysis. Through LRP the single-trial DNN decisions are transformed into heatmaps indicating each data point’s relevance for the outcome of the decision. Results: DNN achieves classification accuracies comparable to those of CSP-LDA. In subjects with low performance subject-to-subject transfer of trained DNNs can improve the results. The single-trial LRP heatmaps reveal neurophysiologically plausible patterns, resembling CSP-derived scalp maps. Critically, while CSP patterns represent class-wise aggregated information, LRP heatmaps pinpoint neural patterns to single time points in single trials. Comparison with Existing Method(s): We compare the classification performance of DNNs to that of linear CSP-LDA on two data sets related to motor-imaginery BCI. Conclusion: We have demonstrated that DNN is a powerful non-linear tool for EEG analysis. With LRP a new quality of high-resolution assessment of neural activity can be reached. LRP is a potential remedy for the lack of interpretability of DNNs that has limited their utility in neuroscientific applications. The extreme specificity of the LRP-derived heatmaps opens up new avenues for investigating neural activity underlying complex perception or decision-related processes.
Tasks	EEG
Published	2016-04-27
URL	http://arxiv.org/abs/1604.08201v1
PDF	http://arxiv.org/pdf/1604.08201v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-deep-neural-networks-for-single
Repo
Framework

Softplus Regressions and Convex Polytopes


Title	Softplus Regressions and Convex Polytopes
Authors	Mingyuan Zhou
Abstract	To construct flexible nonlinear predictive distributions, the paper introduces a family of softplus function based regression models that convolve, stack, or combine both operations by convolving countably infinite stacked gamma distributions, whose scales depend on the covariates. Generalizing logistic regression that uses a single hyperplane to partition the covariate space into two halves, softplus regressions employ multiple hyperplanes to construct a confined space, related to a single convex polytope defined by the intersection of multiple half-spaces or a union of multiple convex polytopes, to separate one class from the other. The gamma process is introduced to support the convolution of countably infinite (stacked) covariate-dependent gamma distributions. For Bayesian inference, Gibbs sampling derived via novel data augmentation and marginalization techniques is used to deconvolve and/or demix the highly complex nonlinear predictive distribution. Example results demonstrate that softplus regressions provide flexible nonlinear decision boundaries, achieving classification accuracies comparable to that of kernel support vector machine while requiring significant less computation for out-of-sample prediction.
Tasks	Bayesian Inference, Data Augmentation
Published	2016-08-23
URL	http://arxiv.org/abs/1608.06383v1
PDF	http://arxiv.org/pdf/1608.06383v1.pdf
PWC	https://paperswithcode.com/paper/softplus-regressions-and-convex-polytopes
Repo
Framework

New Methods to Improve Large-Scale Microscopy Image Analysis with Prior Knowledge and Uncertainty


Title	New Methods to Improve Large-Scale Microscopy Image Analysis with Prior Knowledge and Uncertainty
Authors	Johannes Stegmaier
Abstract	Multidimensional imaging techniques provide powerful ways to examine various kinds of scientific questions. The routinely produced datasets in the terabyte-range, however, can hardly be analyzed manually and require an extensive use of automated image analysis. The present thesis introduces a new concept for the estimation and propagation of uncertainty involved in image analysis operators and new segmentation algorithms that are suitable for terabyte-scale analyses of 3D+t microscopy images.
Tasks
Published	2016-08-30
URL	http://arxiv.org/abs/1608.08471v1
PDF	http://arxiv.org/pdf/1608.08471v1.pdf
PWC	https://paperswithcode.com/paper/new-methods-to-improve-large-scale-microscopy
Repo
Framework


Title	Part-of-Speech Tagging for Code-mixed Indian Social Media Text at ICON 2015
Authors	Kamal Sarkar
Abstract	This paper discusses the experiments carried out by us at Jadavpur University as part of the participation in ICON 2015 task: POS Tagging for Code-mixed Indian Social Media Text. The tool that we have developed for the task is based on Trigram Hidden Markov Model that utilizes information from dictionary as well as some other word level features to enhance the observation probabilities of the known tokens as well as unknown tokens. We submitted runs for Bengali-English, Hindi-English and Tamil-English Language pairs. Our system has been trained and tested on the datasets released for ICON 2015 shared task: POS Tagging For Code-mixed Indian Social Media Text. In constrained mode, our system obtains average overall accuracy (averaged over all three language pairs) of 75.60% which is very close to other participating two systems (76.79% for IIITH and 75.79% for AMRITA_CEN) ranked higher than our system. In unconstrained mode, our system obtains average overall accuracy of 70.65% which is also close to the system (72.85% for AMRITA_CEN) which obtains the highest average overall accuracy.
Tasks	Part-Of-Speech Tagging
Published	2016-01-06
URL	http://arxiv.org/abs/1601.01195v1
PDF	http://arxiv.org/pdf/1601.01195v1.pdf
PWC	https://paperswithcode.com/paper/part-of-speech-tagging-for-code-mixed-indian
Repo
Framework