October 17, 2019

3288 words 16 mins read

Paper Group ANR 745

A comparison of cluster algorithms as applied to unsupervised surveys. A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber. Inference of Quantized Neural Networks on Heterogeneous All-Programmable Devices. Generalized Earthquake Frequency-Magnitude Distribution Describ …

A comparison of cluster algorithms as applied to unsupervised surveys


Title	A comparison of cluster algorithms as applied to unsupervised surveys
Authors	Kathleen Campbell Garwood, Ph. D., Arpit Arun Dhobale
Abstract	When considering answering important questions with data, unsupervised data offers extensive insight opportunity and unique challenges. This study considers student survey data with a specific goal of clustering students into like groups with underlying concept of identifying different poverty levels. Fuzzy logic is considered during the data cleaning and organizing phase helping to create a logical dependent variable for analysis comparison. Using multiple data reduction techniques, the survey was reduced and cleaned. Finally, multiple clustering techniques (k-means, k-modes, and hierarchical clustering) are applied and compared. Though each method has strengths, the goal was to identify which was most viable when applied to survey data and specifically when trying to identify the most impoverished students.
Tasks
Published	2018-11-28
URL	http://arxiv.org/abs/1811.12210v2
PDF	http://arxiv.org/pdf/1811.12210v2.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-cluster-algorithms-as-applied
Repo
Framework

A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber


Title	A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
Authors	MicroBooNE collaboration, C. Adams, M. Alrashed, R. An, J. Anthony, J. Asaadi, A. Ashkenazi, M. Auger, S. Balasubramanian, B. Baller, C. Barnes, G. Barr, M. Bass, F. Bay, A. Bhat, K. Bhattacharya, M. Bishai, A. Blake, T. Bolton, L. Camilleri, D. Caratelli, I. Caro Terrazas, R. Carr, R. Castillo Fernandez, F. Cavanna, G. Cerati, Y. Chen, E. Church, D. Cianci, E. Cohen, G. H. Collin, J. M. Conrad, M. Convery, L. Cooper-Troendle, J. I. Crespo-Anadon, M. Del Tutto, D. Devitt, A. Diaz, K. Duffy, S. Dytman, B. Eberly, A. Ereditato, L. Escudero Sanchez, J. Esquivel, J. J. Evans, A. A. Fadeeva, R. S. Fitzpatrick, B. T. Fleming, D. Franco, A. P. Furmanski, D. Garcia-Gamez, G. T. Garvey, V. Genty, D. Goeldi, S. Gollapinni, O. Goodwin, E. Gramellini, H. Greenlee, R. Grosso, R. Guenette, P. Guzowski, A. Hackenburg, P. Hamilton, O. Hen, J. Hewes, C. Hill, G. A. Horton-Smith, A. Hourlier, E. -C. Huang, C. James, J. Jan de Vries, L. Jiang, R. A. Johnson, J. Joshi, H. Jostlein, Y. -J. Jwa, G. Karagiorgi, W. Ketchum, B. Kirby, M. Kirby, T. Kobilarcik, I. Kreslo, Y. Li, A. Lister, B. R. Littlejohn, S. Lockwitz, D. Lorca, W. C. Louis, M. Luethi, B. Lundberg, X. Luo, A. Marchionni, S. Marcocci, C. Mariani, J. Marshall, J. Martin-Albo, D. A. Martinez Caicedo, A. Mastbaum, V. Meddage, T. Mettler, G. B. Mills, K. Mistry, A. Mogan, J. Moon, M. Mooney, C. D. Moore, J. Mousseau, M. Murphy, R. Murrells, D. Naples, P. Nienaber, J. Nowak, O. Palamara, V. Pandey, V. Paolone, A. Papadopoulou, V. Papavassiliou, S. F. Pate, Z. Pavlovic, E. Piasetzky, D. Porzio, G. Pulliam, X. Qian, J. L. Raaf, A. Rafique, L. Rochester, M. Ross-Lonergan, C. Rudolf von Rohr, B. Russell, D. W. Schmitz, A. Schukraft, W. Seligman, M. H. Shaevitz, R. Sharankova, J. Sinclair, A. Smith, E. L. Snider, M. Soderberg, S. Soldner-Rembold, S. R. Soleti, P. Spentzouris, J. Spitz, J. St. John, T. Strauss, K. Sutton, S. Sword-Fehlberg, A. M. Szelc, N. Tagg, W. Tang, K. Terao, M. Thomson, R. T. Thornton, M. Toups, Y. -T. Tsai, S. Tufanli, T. Usher, W. Van De Pontseele, R. G. Van de Water, B. Viren, M. Weber, H. Wei, D. A. Wickremasinghe, K. Wierman, Z. Williams, S. Wolbers, T. Wongjirad, K. Woodruff, T. Yang, G. Yarbrough, L. E. Yates, G. P. Zeller, J. Zennamo, C. Zhang
Abstract	We have developed a convolutional neural network (CNN) that can make a pixel-level prediction of objects in image data recorded by a liquid argon time projection chamber (LArTPC) for the first time. We describe the network design, training techniques, and software tools developed to train this network. The goal of this work is to develop a complete deep neural network based data reconstruction chain for the MicroBooNE detector. We show the first demonstration of a network’s validity on real LArTPC data using MicroBooNE collection plane images. The demonstration is performed for stopping muon and a $\nu_\mu$ charged current neutral pion data samples.
Tasks
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07269v1
PDF	http://arxiv.org/pdf/1808.07269v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-neural-network-for-pixel-level
Repo
Framework

Inference of Quantized Neural Networks on Heterogeneous All-Programmable Devices


Title	Inference of Quantized Neural Networks on Heterogeneous All-Programmable Devices
Authors	Thomas B. Preußer, Giulio Gambardella, Nicholas Fraser, Michaela Blott
Abstract	Neural networks have established as a generic and powerful means to approach challenging problems such as image classification, object detection or decision making. Their successful employment foots on an enormous demand of compute. The quantization of network parameters and the processed data has proven a valuable measure to reduce the challenges of network inference so effectively that the feasible scope of applications is expanded even into the embedded domain. This paper describes the making of a real-time object detection in a live video stream processed on an embedded all-programmable device. The presented case illustrates how the required processing is tamed and parallelized across both the CPU cores and the programmable logic and how the most suitable resources and powerful extensions, such as NEON vectorization, are leveraged for the individual processing steps. The crafted result is an extended Darknet framework implementing a fully integrated, end-to-end solution from video capture over object annotation to video output applying neural network inference at different quantization levels running at 16~frames per second on an embedded Zynq UltraScale+ (XCZU3EG) platform.
Tasks	Decision Making, Image Classification, Object Detection, Quantization, Real-Time Object Detection
Published	2018-06-21
URL	http://arxiv.org/abs/1806.08085v1
PDF	http://arxiv.org/pdf/1806.08085v1.pdf
PWC	https://paperswithcode.com/paper/inference-of-quantized-neural-networks-on
Repo
Framework

Generalized Earthquake Frequency-Magnitude Distribution Described by Asymmetric Laplace Mixture Modelling


Title	Generalized Earthquake Frequency-Magnitude Distribution Described by Asymmetric Laplace Mixture Modelling
Authors	Arnaud Mignan
Abstract	The complete part of the earthquake frequency-magnitude distribution (FMD), above completeness magnitude mc, is well described by the Gutenberg-Richter law. The parameter mc however varies in space due to the seismic network configuration, yielding a convoluted FMD shape below max(mc). This paper investigates the shape of the generalized FMD (GFMD), which may be described as a mixture of elemental FMDs (eFMDs) defined as asymmetric Laplace distributions of mode mc [Mignan, 2012, https://doi.org/10.1029/2012JB009347]. An asymmetric Laplace mixture model (GFMD- ALMM) is thus proposed with its parameters (detection parameter kappa, Gutenberg-Richter beta-value, mc distribution, as well as number K and weight w of eFMD components) estimated using a semi-supervised hard expectation maximization approach including BIC penalties for model complexity. The performance of the proposed method is analysed, with encouraging results obtained: kappa, beta, and the mc distribution range are retrieved for different GFMD shapes in simulations, as well as in regional catalogues (southern and northern California, Nevada, Taiwan, France), in a global catalogue, and in an aftershock sequence (Christchurch, New Zealand). We find max(mc) to be conservative compared to other methods, kappa = k/log(10) = 3 in most catalogues (compared to beta = b/log(10) = 1), but also that biases in kappa and beta may occur when rounding errors are present below completeness. The GFMD-ALMM, by modelling different FMD shapes in an autonomous manner, opens the door to new statistical analyses in the realm of incomplete seismicity data, which could in theory improve earthquake forecasting by considering c. ten times more events.
Tasks
Published	2018-10-17
URL	http://arxiv.org/abs/1810.07450v1
PDF	http://arxiv.org/pdf/1810.07450v1.pdf
PWC	https://paperswithcode.com/paper/generalized-earthquake-frequency-magnitude
Repo
Framework

Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification


Title	Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification
Authors	Junyang Lin, Qi Su, Pengcheng Yang, Shuming Ma, Xu Sun
Abstract	We propose a novel model for multi-label text classification, which is based on sequence-to-sequence learning. The model generates higher-level semantic unit representations with multi-level dilated convolution as well as a corresponding hybrid attention mechanism that extracts both the information at the word-level and the level of the semantic unit. Our designed dilated convolution effectively reduces dimension and supports an exponential expansion of receptive fields without loss of local information, and the attention-over-attention mechanism is able to capture more summary relevant information from the source context. Results of our experiments show that the proposed model has significant advantages over the baseline models on the dataset RCV1-V2 and Ren-CECps, and our analysis demonstrates that our model is competitive to the deterministic hierarchical models and it is more robust to classifying low-frequency labels.
Tasks	Multi-Label Text Classification, Text Classification
Published	2018-08-26
URL	http://arxiv.org/abs/1808.08561v2
PDF	http://arxiv.org/pdf/1808.08561v2.pdf
PWC	https://paperswithcode.com/paper/semantic-unit-based-dilated-convolution-for
Repo
Framework

Deep Learning Based Power Control for Quality-Driven Wireless Video Transmissions


Title	Deep Learning Based Power Control for Quality-Driven Wireless Video Transmissions
Authors	Chuang Ye, M. Cenk Gursoy, Senem Velipasalar
Abstract	In this paper, wireless video transmission to multiple users under total transmission power and minimum required video quality constraints is studied. In order to provide the desired performance levels to the end-users in real-time video transmissions while using the energy resources efficiently, we assume that power control is employed. Due to the presence of interference, determining the optimal power control is a non-convex problem but can be solved via monotonic optimization framework. However, monotonic optimization is an iterative algorithm and can often entail considerable computational complexity, making it not suitable for real-time applications. To address this, we propose a learning-based approach that treats the input and output of a resource allocation algorithm as an unknown nonlinear mapping and a deep neural network (DNN) is employed to learn this mapping. This learned mapping via DNN can provide the optimal power level quickly for given channel conditions.
Tasks
Published	2018-10-16
URL	http://arxiv.org/abs/1810.07548v1
PDF	http://arxiv.org/pdf/1810.07548v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-power-control-for-quality
Repo
Framework

Evaluating Architectural Choices for Deep Learning Approaches for Question Answering over Knowledge Bases


Title	Evaluating Architectural Choices for Deep Learning Approaches for Question Answering over Knowledge Bases
Authors	Sherzod Hakimov, Soufian Jebbara, Philipp Cimiano
Abstract	The task of answering natural language questions over knowledge bases has received wide attention in recent years. Various deep learning architectures have been proposed for this task. However, architectural design choices are typically not systematically compared nor evaluated under the same conditions. In this paper, we contribute to a better understanding of the impact of architectural design choices by evaluating four different architectures under the same conditions. We address the task of answering simple questions, consisting in predicting the subject and predicate of a triple given a question. In order to provide a fair comparison of different architectures, we evaluate them under the same strategy for inferring the subject, and compare different architectures for inferring the predicate. The architecture for inferring the subject is based on a standard LSTM model trained to recognize the span of the subject in the question and on a linking component that links the subject span to an entity in the knowledge base. The architectures for predicate inference are based on i) a standard softmax classifier ranging over all predicates as output, iii) a model that predicts a low-dimensional encoding of the property given entity representation and question, iii) a model that learns to score a pair of subject and predicate given the question as well as iv) a model based on the well-known FastText model. The comparison of architectures shows that FastText provides better results than other architectures.
Tasks	Question Answering
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02536v2
PDF	http://arxiv.org/pdf/1812.02536v2.pdf
PWC	https://paperswithcode.com/paper/evaluating-architectural-choices-for-deep
Repo
Framework

Fast Power system security analysis with Guided Dropout


Title	Fast Power system security analysis with Guided Dropout
Authors	Benjamin Donnot, Isabelle Guyon, Marc Schoenauer, Antoine Marot, Patrick Panciatici
Abstract	We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation solvers. We use a deep feed-forward neural network trained with load-flows precomputed by simulation. Our architecture permits to train a network on so-called “n-1” problems, in which load flows are evaluated for every possible line disconnection, then generalize to “n-2” problems without retraining (a clear advantage because of the combinatorial nature of the problem). To that end, we developed a technique bearing similarity with “dropout”, which we named “guided dropout”.
Tasks
Published	2018-01-30
URL	http://arxiv.org/abs/1801.09870v1
PDF	http://arxiv.org/pdf/1801.09870v1.pdf
PWC	https://paperswithcode.com/paper/fast-power-system-security-analysis-with
Repo
Framework

Query Tracking for E-commerce Conversational Search: A Machine Comprehension Perspective


Title	Query Tracking for E-commerce Conversational Search: A Machine Comprehension Perspective
Authors	Yunlun Yang, Yu Gong, Xi Chen
Abstract	With the development of dialog techniques, conversational search has attracted more and more attention as it enables users to interact with the search engine in a natural and efficient manner. However, comparing with the natural language understanding in traditional task-oriented dialog which focuses on slot filling and tracking, the query understanding in E-commerce conversational search is quite different and more challenging due to more diverse user expressions and complex intentions. In this work, we define the real-world problem of query tracking in E-commerce conversational search, in which the goal is to update the internal query after each round of interaction. We also propose a self attention based neural network to handle the task in a machine comprehension perspective. Further more we build a novel E-commerce query tracking dataset from an operational E-commerce Search Engine, and experimental results on this dataset suggest that our proposed model outperforms several baseline methods by a substantial gain for Exact Match accuracy and F1 score, showing the potential of machine comprehension like model for this task.
Tasks	Reading Comprehension, Slot Filling
Published	2018-10-08
URL	http://arxiv.org/abs/1810.03274v1
PDF	http://arxiv.org/pdf/1810.03274v1.pdf
PWC	https://paperswithcode.com/paper/query-tracking-for-e-commerce-conversational
Repo
Framework

Distinctiveness, complexity, and repeatability of online signature templates


Title	Distinctiveness, complexity, and repeatability of online signature templates
Authors	NapaSae-Bae, NasirMemon, Pitikhate Sooraksa
Abstract	This paper proposes three measures to quantify the characteristics of online signature templates in terms of distinctiveness, complexity and repeatability. A distinctiveness measure of a signature template is computed from a set of enrolled signature samples and a statistical assumption about random signatures. Secondly, a complexity measure of the template is derived from a set of enrolled signature samples. Finally, given a signature template, a measure to quantify the repeatability of the online signature is derived from a validation set of samples. These three measures can then be used as an indicator for the performance of the system in rejecting random forgery samples and skilled forgery samples and the performance of users in providing accepted genuine samples, respectively. The effectiveness of these three measures and their applications are demonstrated through experiments performed on three online signature datasets and one keystroke dynamics dataset using different verification algorithms.
Tasks
Published	2018-08-10
URL	http://arxiv.org/abs/1808.03399v1
PDF	http://arxiv.org/pdf/1808.03399v1.pdf
PWC	https://paperswithcode.com/paper/distinctiveness-complexity-and-repeatability
Repo
Framework

Infinite Arms Bandit: Optimality via Confidence Bounds


Title	Infinite Arms Bandit: Optimality via Confidence Bounds
Authors	Hock Peng Chan, Shouri Hu
Abstract	The infinite arms bandit problem was initiated by Berry et al. (1997). They derived a regret lower bound of all solutions for Bernoulli rewards with uniform priors, and proposed bandit strategies based on success runs, but which do not achieve this bound. Bonald and Prouti`{e}re (2013) showed that the lower bound was achieved by their two-target algorithm, and extended optimality to Bernoulli rewards with general priors. We propose here a confidence bound target (CBT) algorithm that achieves optimality for unspecified non-negative reward distributions. For each arm we apply the mean and standard deviation of its rewards to compute a confidence bound and play the arm with the smallest confidence bound provided it is smaller than a target mean. If the bounds are all larger, then we play a new arm. We show for a given prior of the arm means how the target mean can be computed to achieve optimality. In the absence of information on the prior the target mean is determined empirically, and the regret achieved is still comparable to the regret lower bound. Numerical studies show that CBT is versatile and outperforms its competitors.
Tasks
Published	2018-05-30
URL	https://arxiv.org/abs/1805.11793v3
PDF	https://arxiv.org/pdf/1805.11793v3.pdf
PWC	https://paperswithcode.com/paper/infinite-arms-bandit-optimality-via
Repo
Framework

Generalized Gaussian Kernel Adaptive Filtering


Title	Generalized Gaussian Kernel Adaptive Filtering
Authors	Tomoya Wada, Kosuke Fukumori, Toshihisa Tanaka, Simone Fiori
Abstract	The present paper proposes generalized Gaussian kernel adaptive filtering, where the kernel parameters are adaptive and data-driven. The Gaussian kernel is parametrized by a center vector and a symmetric positive definite (SPD) precision matrix, which is regarded as a generalization of the scalar width parameter. These parameters are adaptively updated on the basis of a proposed least-square-type rule to minimize the estimation error. The main contribution of this paper is to establish update rules for precision matrices on the SPD manifold in order to keep their symmetric positive-definiteness. Different from conventional kernel adaptive filters, the proposed regressor is a superposition of Gaussian kernels with all different parameters, which makes such regressor more flexible. The kernel adaptive filtering algorithm is established together with a l1-regularized least squares to avoid overfitting and the increase of dimensionality of the dictionary. Experimental results confirm the validity of the proposed method.
Tasks
Published	2018-04-25
URL	http://arxiv.org/abs/1804.09348v1
PDF	http://arxiv.org/pdf/1804.09348v1.pdf
PWC	https://paperswithcode.com/paper/generalized-gaussian-kernel-adaptive
Repo
Framework

Aggregated Sparse Attention for Steering Angle Prediction


Title	Aggregated Sparse Attention for Steering Angle Prediction
Authors	Sen He, Dmitry Kangin, Yang Mi, Nicolas Pugeault
Abstract	In this paper, we apply the attention mechanism to autonomous driving for steering angle prediction. We propose the first model, applying the recently introduced sparse attention mechanism to visual domain, as well as the aggregated extension for this model. We show the improvement of the proposed method, comparing to no attention as well as to different types of attention.
Tasks	Autonomous Driving
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05785v1
PDF	http://arxiv.org/pdf/1803.05785v1.pdf
PWC	https://paperswithcode.com/paper/aggregated-sparse-attention-for-steering
Repo
Framework

Joint Binary Neural Network for Multi-label Learning with Applications to Emotion Classification


Title	Joint Binary Neural Network for Multi-label Learning with Applications to Emotion Classification
Authors	Huihui He, Rui Xia
Abstract	Recently the deep learning techniques have achieved success in multi-label classification due to its automatic representation learning ability and the end-to-end learning framework. Existing deep neural networks in multi-label classification can be divided into two kinds: binary relevance neural network (BRNN) and threshold dependent neural network (TDNN). However, the former needs to train a set of isolate binary networks which ignore dependencies between labels and have heavy computational load, while the latter needs an additional threshold function mechanism to transform the multi-class probabilities to multi-label outputs. In this paper, we propose a joint binary neural network (JBNN), to address these shortcomings. In JBNN, the representation of the text is fed to a set of logistic functions instead of a softmax function, and the multiple binary classifications are carried out synchronously in one neural network framework. Moreover, the relations between labels are captured via training on a joint binary cross entropy (JBCE) loss. To better meet multi-label emotion classification, we further proposed to incorporate the prior label relations into the JBCE loss. The experimental results on the benchmark dataset show that our model performs significantly better than the state-of-the-art multi-label emotion classification methods, in both classification performance and computational efficiency.
Tasks	Emotion Classification, Multi-Label Classification, Multi-Label Learning, Representation Learning
Published	2018-02-03
URL	http://arxiv.org/abs/1802.00891v1
PDF	http://arxiv.org/pdf/1802.00891v1.pdf
PWC	https://paperswithcode.com/paper/joint-binary-neural-network-for-multi-label
Repo
Framework

Stochastic Primal-Dual Method for Empirical Risk Minimization with $\mathcal{O}(1)$ Per-Iteration Complexity


Title	Stochastic Primal-Dual Method for Empirical Risk Minimization with $\mathcal{O}(1)$ Per-Iteration Complexity
Authors	Conghui Tan, Tong Zhang, Shiqian Ma, Ji Liu
Abstract	Regularized empirical risk minimization problem with linear predictor appears frequently in machine learning. In this paper, we propose a new stochastic primal-dual method to solve this class of problems. Different from existing methods, our proposed methods only require O(1) operations in each iteration. We also develop a variance-reduction variant of the algorithm that converges linearly. Numerical experiments suggest that our methods are faster than existing ones such as proximal SGD, SVRG and SAGA on high-dimensional problems.
Tasks
Published	2018-11-03
URL	http://arxiv.org/abs/1811.01182v1
PDF	http://arxiv.org/pdf/1811.01182v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-primal-dual-method-for-empirical-1
Repo
Framework