January 26, 2020

3223 words 16 mins read

Paper Group ANR 1348

The dynamics of the stomatognathic system from 4D multimodal data. Learning to Order Sub-questions for Complex Question Answering. Joint Language Identification of Code-Switching Speech using Attention based E2E Network. How Widely Can Prediction Models be Generalized? Performance Prediction in Blended Courses. Nonconvex sampling with the Metropoli …

The dynamics of the stomatognathic system from 4D multimodal data


Title	The dynamics of the stomatognathic system from 4D multimodal data
Authors	Agnieszka A. Tomaka, Leszek Luchowski, Dariusz Pojda, Michał Tarnawski, Krzysztof Domino
Abstract	The purpose of this chapter is to discuss methods of acquisition, visualization and analysis of the dynamics of a complex biomedical system, illustrated by the human stomatognathic system. The stomatognathic system consists of the teeth and the skull bones with the maxilla and the mandible. Its dynamics can be described by the change of mutual position of the lower/mandibular part versus the upper/maxillary one due to the physiological motion of opening, chewing and swallowing. In order to analyse the dynamics of the stomatognathic system its morphology and motion has to be digitized, which is done using static and dynamic multimodal imagery like CBCT and 3D scans data and temporal measurements of motion. The integration of multimodal data incorporates different direct and indirect methods of registration - aligning of all the data in the same coordinate system. The integrated sets of data form 4D multimodal data which can be further visualized, modeled, and subjected to multivariate time series analysis. Example results are shown. Although there is no direct method of imaging the TMJ motion, the integration of multimodal data forms an adequate tool. As medical imaging becomes ever more diverse and ever more accessible, organizing the imagery and measurements into unified, comprehensive records can deliver to the doctor the most information in the most accessible form, creating a new quality in data simulation, analysis and interpretation.
Tasks	Time Series, Time Series Analysis
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08854v1
PDF	https://arxiv.org/pdf/1911.08854v1.pdf
PWC	https://paperswithcode.com/paper/the-dynamics-of-the-stomatognathic-system
Repo
Framework

Learning to Order Sub-questions for Complex Question Answering


Title	Learning to Order Sub-questions for Complex Question Answering
Authors	Yunan Zhang, Xiang Cheng, Yufeng Zhang, Zihan Wang, Zhengqi Fang, Xiaoyan Wang, Zhenya Huang, Chengxiang Zhai
Abstract	Answering complex questions involving multiple entities and relations is a challenging task. Logically, the answer to a complex question should be derived by decomposing the complex question into multiple simple sub-questions and then answering those sub-questions. Existing work has followed this strategy but has not attempted to optimize the order of how those sub-questions are answered. As a result, the sub-questions are answered in an arbitrary order, leading to larger search space and a higher risk of missing an answer. In this paper, we propose a novel reinforcement learning(RL) approach to answering complex questions that can learn a policy to dynamically decide which sub-question should be answered at each stage of reasoning. We lever-age the expected value-variance criterion to enable the learned policy to balance between the risk and utility of answering a sub-question. Experiment results show that the RL approach can substantially improve the optimality of ordering the sub-questions, leading to improved accuracy of question answering. The proposed method for learning to order sub-questions is general and can thus be potentially combined with many existing ideas for answering complex questions to enhance their performance.
Tasks	Question Answering
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04065v2
PDF	https://arxiv.org/pdf/1911.04065v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-order-sub-questions-for-complex
Repo
Framework

Joint Language Identification of Code-Switching Speech using Attention based E2E Network


Title	Joint Language Identification of Code-Switching Speech using Attention based E2E Network
Authors	Sreeram Ganji, Kunal Dhawan, Kumar Priyadarshi, Rohit Sinha
Abstract	Language identification (LID) has relevance in many speech processing applications. For the automatic recognition of code-switching speech, the conventional approaches often employ an LID system for detecting the languages present within an utterance. In the existing works, the LID on code-switching speech involves modelling of the underlying languages separately. In this work, we propose a joint modelling based LID system for code-switching speech. To achieve the same, an attention-based end-to-end (E2E) network has been explored. For the development and evaluation of the proposed approach, a recently created Hindi-English code-switching corpus has been used. For the contrast purpose, an LID system employing the connectionist temporal classification-based E2E network is also developed. On comparing both the LID systems, the attention based approach is noted to result in better LID accuracy. The effective location of code-switching boundaries within the utterance by the proposed approach has been demonstrated by plotting the attention weights of E2E network.
Tasks	Language Identification
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06342v1
PDF	https://arxiv.org/pdf/1907.06342v1.pdf
PWC	https://paperswithcode.com/paper/joint-language-identification-of-code
Repo
Framework

How Widely Can Prediction Models be Generalized? Performance Prediction in Blended Courses


Title	How Widely Can Prediction Models be Generalized? Performance Prediction in Blended Courses
Authors	Niki Gitinabard, Yiqiao Xu, Sarah Heckman, Tiffany Barnes, Collin F. Lynch
Abstract	Blended courses that mix in-person instruction with online platforms are increasingly popular in secondary education. These tools record a rich amount of data on students’ study habits and social interactions. Prior research has shown that these metrics are correlated with students’ performance in face to face classes. However, predictive models for blended courses are still limited and have not yet succeeded at early prediction or cross-class predictions even for repeated offerings of the same course. In this work, we use data from two offerings of two different undergraduate courses to train and evaluate predictive models on student performance based upon persistent student characteristics including study habits and social interactions. We analyze the performance of these models on the same offering, on different offerings of the same course, and across courses to see how well they generalize. We also evaluate the models on different segments of the courses to determine how early reliable predictions can be made. This work tells us in part how much data is required to make robust predictions and how cross-class data may be used, or not, to boost model performance. The results of this study will help us better understand how similar the study habits, social activities, and the teamwork styles are across semesters for students in each performance category. These trained models also provide an avenue to improve our existing support platforms to better support struggling students early in the semester with the goal of providing timely intervention.
Tasks
Published	2019-04-15
URL	https://arxiv.org/abs/1904.07328v2
PDF	https://arxiv.org/pdf/1904.07328v2.pdf
PWC	https://paperswithcode.com/paper/how-widely-can-prediction-models-be
Repo
Framework

Nonconvex sampling with the Metropolis-adjusted Langevin algorithm


Title	Nonconvex sampling with the Metropolis-adjusted Langevin algorithm
Authors	Oren Mangoubi, Nisheeth K. Vishnoi
Abstract	The Langevin Markov chain algorithms are widely deployed methods to sample from distributions in challenging high-dimensional and non-convex statistics and machine learning applications. Despite this, current bounds for the Langevin algorithms are slower than those of competing algorithms in many important situations, for instance when sampling from weakly log-concave distributions, or when sampling or optimizing non-convex log-densities. In this paper, we obtain improved bounds in many of these situations, showing that the Metropolis-adjusted Langevin algorithm (MALA) is faster than the best bounds for its competitor algorithms when the target distribution satisfies weak third- and fourth- order regularity properties associated with the input data. In many settings, our regularity conditions are weaker than the usual Euclidean operator norm regularity properties, allowing us to show faster bounds for a much larger class of distributions than would be possible with the usual Euclidean operator norm approach, including in statistics and machine learning applications where the data satisfy a certain incoherence condition. In particular, we show that using our regularity conditions one can obtain faster bounds for applications which include sampling problems in Bayesian logistic regression with weakly convex priors, and the nonconvex optimization problem of learning linear classifiers with zero-one loss functions. Our main technical contribution in this paper is our analysis of the Metropolis acceptance probability of MALA in terms of its “energy-conservation error,” and our bound for this error in terms of third- and fourth- order regularity conditions. Our combination of this higher-order analysis of the energy conservation error with the conductance method is key to obtaining bounds which have a sub-linear dependence on the dimension $d$ in the non-strongly logconcave setting.
Tasks
Published	2019-02-22
URL	http://arxiv.org/abs/1902.08452v2
PDF	http://arxiv.org/pdf/1902.08452v2.pdf
PWC	https://paperswithcode.com/paper/nonconvex-sampling-with-the-metropolis
Repo
Framework

Improving Transparency of Deep Neural Inference Process


Title	Improving Transparency of Deep Neural Inference Process
Authors	Hiroshi Kuwajima, Masayuki Tanaka, Masatoshi Okutomi
Abstract	Deep learning techniques are rapidly advanced recently, and becoming a necessity component for widespread systems. However, the inference process of deep learning is black-box, and not very suitable to safety-critical systems which must exhibit high transparency. In this paper, to address this black-box limitation, we develop a simple analysis method which consists of 1) structural feature analysis: lists of the features contributing to inference process, 2) linguistic feature analysis: lists of the natural language labels describing the visual attributes for each feature contributing to inference process, and 3) consistency analysis: measuring consistency among input data, inference (label), and the result of our structural and linguistic feature analysis. Our analysis is simplified to reflect the actual inference process for high transparency, whereas it does not include any additional black-box mechanisms such as LSTM for highly human readable results. We conduct experiments and discuss the results of our analysis qualitatively and quantitatively, and come to believe that our work improves the transparency of neural networks. Evaluated through 12,800 human tasks, 75% workers answer that input data and result of our feature analysis are consistent, and 70% workers answer that inference (label) and result of our feature analysis are consistent. In addition to the evaluation of the proposed analysis, we find that our analysis also provide suggestions, or possible next actions such as expanding neural network complexity or collecting training data to improve a neural network.
Tasks
Published	2019-03-13
URL	http://arxiv.org/abs/1903.05501v1
PDF	http://arxiv.org/pdf/1903.05501v1.pdf
PWC	https://paperswithcode.com/paper/improving-transparency-of-deep-neural
Repo
Framework

Robust Attacks against Multiple Classifiers


Title	Robust Attacks against Multiple Classifiers
Authors	Juan C. Perdomo, Yaron Singer
Abstract	We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be framed as finding strategies at equilibrium in a two-player, zero-sum game between a learner and an adversary. In doing so, we illustrate the need for randomization in adversarial attacks. In order to compute Nash equilibrium, our main technical focus is on the design of best response oracles that can then be implemented within a Multiplicative Weights Update framework to boost deterministic perturbations against a set of models into optimal mixed strategies. We demonstrate the practical effectiveness of our approach on a series of image classification tasks using both linear classifiers and deep neural networks.
Tasks	Image Classification
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02816v1
PDF	https://arxiv.org/pdf/1906.02816v1.pdf
PWC	https://paperswithcode.com/paper/robust-attacks-against-multiple-classifiers
Repo
Framework

Dynamic Hilbert Maps: Real-Time Occupancy Predictions in Changing Environment


Title	Dynamic Hilbert Maps: Real-Time Occupancy Predictions in Changing Environment
Authors	Vitor Guizilini, Ransalu Senanayake, Fabio Ramos
Abstract	This paper addresses the problem of learning instantaneous occupancy levels of dynamic environments and predicting future occupancy levels. Due to the complexity of most real-world environments, such as urban streets or crowded areas, the efficient and robust incorporation of temporal dependencies into otherwise static occupancy models remains a challenge. We propose a method to capture the spatial uncertainty of moving objects and incorporate this uncertainty information into a continuous occupancy map represented in a rich high-dimensional feature space. Experiments performed using LIDAR data verified the real-time performance of the algorithm.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02149v1
PDF	https://arxiv.org/pdf/1912.02149v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-hilbert-maps-real-time-occupancy
Repo
Framework

Input Prioritization for Testing Neural Networks


Title	Input Prioritization for Testing Neural Networks
Authors	Taejoon Byun, Vaibhav Sharma, Abhishek Vijayakumar, Sanjai Rayadurgam, Darren Cofer
Abstract	Deep neural networks (DNNs) are increasingly being adopted for sensing and control functions in a variety of safety and mission-critical systems such as self-driving cars, autonomous air vehicles, medical diagnostics, and industrial robotics. Failures of such systems can lead to loss of life or property, which necessitates stringent verification and validation for providing high assurance. Though formal verification approaches are being investigated, testing remains the primary technique for assessing the dependability of such systems. Due to the nature of the tasks handled by DNNs, the cost of obtaining test oracle data—the expected output, a.k.a. label, for a given input—is high, which significantly impacts the amount and quality of testing that can be performed. Thus, prioritizing input data for testing DNNs in meaningful ways to reduce the cost of labeling can go a long way in increasing testing efficacy. This paper proposes using gauges of the DNN’s sentiment derived from the computation performed by the model, as a means to identify inputs that are likely to reveal weaknesses. We empirically assessed the efficacy of three such sentiment measures for prioritization—confidence, uncertainty, and surprise—and compare their effectiveness in terms of their fault-revealing capability and retraining effectiveness. The results indicate that sentiment measures can effectively flag inputs that expose unacceptable DNN behavior. For MNIST models, the average percentage of inputs correctly flagged ranged from 88% to 94.8%.
Tasks	Self-Driving Cars
Published	2019-01-11
URL	http://arxiv.org/abs/1901.03768v1
PDF	http://arxiv.org/pdf/1901.03768v1.pdf
PWC	https://paperswithcode.com/paper/input-prioritization-for-testing-neural
Repo
Framework

Kriging: Beyond Matérn


Title	Kriging: Beyond Matérn
Authors	Pulong Ma, Anindya Bhadra
Abstract	The Mat'ern covariance function is a popular choice for prediction in spatial statistics and uncertainty quantification literature. A key benefit of the Mat'ern class is that it is possible to get precise control over the degree of differentiability of the process realizations. However, the Mat'ern class possesses exponentially decaying tails, and thus may not be suitable for modeling long range dependence. This problem can be remedied using polynomial covariances; however one loses control over the degree of differentiability of the process realizations, in that the realizations using polynomial covariances are either infinitely differentiable or not differentiable at all. We construct a new family of covariance functions using a scale mixture representation of the Mat'ern class where one obtains the benefits of both Mat'ern and polynomial covariances. The resultant covariance contains two parameters: one controls the degree of differentiability near the origin and the other controls the tail heaviness, independently of each other. Using a spectral representation, we derive theoretical properties of this new covariance including equivalence measures and asymptotic behavior of the maximum likelihood estimators under infill asymptotics. The improved theoretical properties in predictive performance of this new covariance class are verified via extensive simulations. Application using NASA’s Orbiting Carbon Observatory-2 satellite data confirms the advantage of this new covariance class over the Mat'ern class, especially in extrapolative settings.
Tasks
Published	2019-11-14
URL	https://arxiv.org/abs/1911.05865v1
PDF	https://arxiv.org/pdf/1911.05865v1.pdf
PWC	https://paperswithcode.com/paper/kriging-beyond-matern
Repo
Framework

Faster Genetic Programming GPquick via multicore and Advanced Vector Extensions


Title	Faster Genetic Programming GPquick via multicore and Advanced Vector Extensions
Authors	W. B. Langdon, W. Banzhaf
Abstract	We evolve floating point Sextic polynomial populations of genetic programming binary trees for up to a million generations. Programs with almost four hundred million instructions are created by crossover. To support unbounded Long-Term Evolution Experiment LTEE GP we use both SIMD parallel AVX 512 bit instructions and 48 threads to yield performance of up to 139 billion GP operations per second, 139 giga GPops, on a single Intel Xeon Gold 6126 2.60GHz server.
Tasks
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09215v1
PDF	http://arxiv.org/pdf/1902.09215v1.pdf
PWC	https://paperswithcode.com/paper/faster-genetic-programming-gpquick-via
Repo
Framework

A simple and effective postprocessing method for image classification


Title	A simple and effective postprocessing method for image classification
Authors	Yan Liu, Yun Li, Yunhao Yuan, jipeng qiang
Abstract	Whether it is computer vision, natural language processing or speech recognition, the essence of these applications is to obtain powerful feature representations that make downstream applications completion more efficient. Taking image recognition as an example, whether it is hand-crafted low-level feature representation or feature representation extracted by a convolutional neural networks(CNNs), the goal is to extract features that better represent image features, thereby improving classification accuracy. However, we observed that image feature representations share a large common vector and a few top dominating directions. To address this problems, we propose a simple but effective postprocessing method to render off-the-shelf feature representations even stronger by eliminating the common mean vector from off-the-shelf feature representations. The postprocessing is empirically validated on a variety of datasets and feature extraction methods.such as VGG, LBP, and HOG. Some experiments show that the features that have been post-processed by postprocessing algorithm can get better results than original ones.
Tasks	Image Classification, Speech Recognition
Published	2019-06-19
URL	https://arxiv.org/abs/1906.07934v1
PDF	https://arxiv.org/pdf/1906.07934v1.pdf
PWC	https://paperswithcode.com/paper/a-simple-and-effective-postprocessing-method
Repo
Framework

Identifying the number of clusters for K-Means: A hypersphere density based approach


Title	Identifying the number of clusters for K-Means: A hypersphere density based approach
Authors	Sukavanan Nanjundan, Shreeviknesh Sankaran, C. R. Arjun, G. Paavai Anand
Abstract	Application of K-Means algorithm is restricted by the fact that the number of clusters should be known beforehand. Previously suggested methods to solve this problem are either ad hoc or require parametric assumptions and complicated calculations. The proposed method aims to solve this conundrum by considering cluster hypersphere density as the factor to determine the number of clusters in the given dataset. The density is calculated by assuming a hypersphere around the cluster centroid for n-different number of clusters. The calculated values are plotted against their corresponding number of clusters and then the optimum number of clusters is obtained after assaying the elbow region of the graph. The method is simple, easy to comprehend, and provides robust and reliable results.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00643v2
PDF	https://arxiv.org/pdf/1912.00643v2.pdf
PWC	https://paperswithcode.com/paper/identifying-the-number-of-clusters-for-k
Repo
Framework

Eigen Values Features for the Classification of Brain Signals corresponding to 2D and 3D Educational Contents


Title	Eigen Values Features for the Classification of Brain Signals corresponding to 2D and 3D Educational Contents
Authors	Saeed Bamatraf, Muhammad Hussain, Emad-ul-Haq Qazi, Hatim Aboalsamh
Abstract	In this paper, we have proposed a brain signal classification method, which uses eigenvalues of the covariance matrix as features to classify images (topomaps) created from the brain signals. The signals are recorded during the answering of 2D and 3D questions. The system is used to classify the correct and incorrect answers for both 2D and 3D questions. Using the classification technique, the impacts of 2D and 3D multimedia educational contents on learning, memory retention and recall will be compared. The subjects learn similar 2D and 3D educational contents. Afterwards, subjects are asked 20 multiple-choice questions (MCQs) associated with the contents after thirty minutes (Short-Term Memory) and two months (Long-Term Memory). Eigenvalues features extracted from topomaps images are given to K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) classifiers, in order to identify the states of the brain related to incorrect and correct answers. Excellent accuracies obtained by both classifiers and by applying statistical analysis on the results, no significant difference is indicated between 2D and 3D multimedia educational contents on learning, memory retention and recall in both STM and LTM.
Tasks
Published	2019-04-30
URL	http://arxiv.org/abs/1904.13221v1
PDF	http://arxiv.org/pdf/1904.13221v1.pdf
PWC	https://paperswithcode.com/paper/eigen-values-features-for-the-classification
Repo
Framework

Malware Evasion Attack and Defense


Title	Malware Evasion Attack and Defense
Authors	Yonghong Huang, Utkarsh Verma, Celeste Fralick, Gabriel Infante-Lopezy, Brajesh Kumarz, Carl Woodward
Abstract	Machine learning (ML) classifiers are vulnerable to adversarial examples. An adversarial example is an input sample which is slightly modified to induce misclassification in an ML classifier. In this work, we investigate white-box and grey-box evasion attacks to an ML-based malware detector and conduct performance evaluations in a real-world setting. We compare the defense approaches in mitigating the attacks. We propose a framework for deploying grey-box and black-box attacks to malware detection systems.
Tasks	Malware Detection
Published	2019-04-07
URL	http://arxiv.org/abs/1904.05747v2
PDF	http://arxiv.org/pdf/1904.05747v2.pdf
PWC	https://paperswithcode.com/paper/malware-evasion-attack-and-defense
Repo
Framework