July 29, 2019

3101 words 15 mins read

Paper Group ANR 52

A Security Monitoring Framework For Virtualization Based HEP Infrastructures. Speech Recognition Challenge in the Wild: Arabic MGB-3. An Edge Driven Wavelet Frame Model for Image Restoration. Simultaneous Detection and Quantification of Retinal Fluid with Deep Learning. Gradient-enhanced kriging for high-dimensional problems. Multiple Context-Free …

A Security Monitoring Framework For Virtualization Based HEP Infrastructures


Title	A Security Monitoring Framework For Virtualization Based HEP Infrastructures
Authors	A. Gomez Ramirez, M. Martinez Pedreira, C. Grigoras, L. Betev, C. Lara, U. Kebschull for the ALICE Collaboration
Abstract	High Energy Physics (HEP) distributed computing infrastructures require automatic tools to monitor, analyze and react to potential security incidents. These tools should collect and inspect data such as resource consumption, logs and sequence of system calls for detecting anomalies that indicate the presence of a malicious agent. They should also be able to perform automated reactions to attacks without administrator intervention. We describe a novel framework that accomplishes these requirements, with a proof of concept implementation for the ALICE experiment at CERN. We show how we achieve a fully virtualized environment that improves the security by isolating services and Jobs without a significant performance impact. We also describe a collected dataset for Machine Learning based Intrusion Prevention and Detection Systems on Grid computing. This dataset is composed of resource consumption measurements (such as CPU, RAM and network traffic), logfiles from operating system services, and system call data collected from production Jobs running in an ALICE Grid test site and a big set of malware. This malware was collected from security research sites. Based on this dataset, we will proceed to develop Machine Learning algorithms able to detect malicious Jobs.
Tasks
Published	2017-04-16
URL	http://arxiv.org/abs/1704.04782v1
PDF	http://arxiv.org/pdf/1704.04782v1.pdf
PWC	https://paperswithcode.com/paper/a-security-monitoring-framework-for
Repo
Framework

Speech Recognition Challenge in the Wild: Arabic MGB-3


Title	Speech Recognition Challenge in the Wild: Arabic MGB-3
Authors	Ahmed Ali, Stephan Vogel, Steve Renals
Abstract	This paper describes the Arabic MGB-3 Challenge - Arabic Speech Recognition in the Wild. Unlike last year’s Arabic MGB-2 Challenge, for which the recognition task was based on more than 1,200 hours broadcast TV news recordings from Aljazeera Arabic TV programs, MGB-3 emphasises dialectal Arabic using a multi-genre collection of Egyptian YouTube videos. Seven genres were used for the data collection: comedy, cooking, family/kids, fashion, drama, sports, and science (TEDx). A total of 16 hours of videos, split evenly across the different genres, were divided into adaptation, development and evaluation data sets. The Arabic MGB-Challenge comprised two tasks: A) Speech transcription, evaluated on the MGB-3 test set, along with the 10 hour MGB-2 test set to report progress on the MGB-2 evaluation; B) Arabic dialect identification, introduced this year in order to distinguish between four major Arabic dialects - Egyptian, Levantine, North African, Gulf, as well as Modern Standard Arabic. Two hours of audio per dialect were released for development and a further two hours were used for evaluation. For dialect identification, both lexical features and i-vector bottleneck features were shared with participants in addition to the raw audio recordings. Overall, thirteen teams submitted ten systems to the challenge. We outline the approaches adopted in each system, and summarise the evaluation results.
Tasks	Speech Recognition
Published	2017-09-21
URL	http://arxiv.org/abs/1709.07276v1
PDF	http://arxiv.org/pdf/1709.07276v1.pdf
PWC	https://paperswithcode.com/paper/speech-recognition-challenge-in-the-wild
Repo
Framework

An Edge Driven Wavelet Frame Model for Image Restoration


Title	An Edge Driven Wavelet Frame Model for Image Restoration
Authors	Jae Kyu Choi, Bin Dong, Xiaoqun Zhang
Abstract	Wavelet frame systems are known to be effective in capturing singularities from noisy and degraded images. In this paper, we introduce a new edge driven wavelet frame model for image restoration by approximating images as piecewise smooth functions. With an implicit representation of image singularities sets, the proposed model inflicts different strength of regularization on smooth and singular image regions and edges. The proposed edge driven model is robust to both image approximation and singularity estimation. The implicit formulation also enables an asymptotic analysis of the proposed models and a rigorous connection between the discrete model and a general continuous variational model. Finally, numerical results on image inpainting and deblurring show that the proposed model is compared favorably against several popular image restoration models.
Tasks	Deblurring, Image Inpainting, Image Restoration
Published	2017-01-25
URL	http://arxiv.org/abs/1701.07158v1
PDF	http://arxiv.org/pdf/1701.07158v1.pdf
PWC	https://paperswithcode.com/paper/an-edge-driven-wavelet-frame-model-for-image
Repo
Framework

Simultaneous Detection and Quantification of Retinal Fluid with Deep Learning


Title	Simultaneous Detection and Quantification of Retinal Fluid with Deep Learning
Authors	Dustin Morley, Hassan Foroosh, Saad Shaikh, Ulas Bagci
Abstract	We propose a new deep learning approach for automatic detection and segmentation of fluid within retinal OCT images. The proposed framework utilizes both ResNet and Encoder-Decoder neural network architectures. When training the network, we apply a novel data augmentation method called myopic warping together with standard rotation-based augmentation to increase the training set size to 45 times the original amount. Finally, the network output is post-processed with an energy minimization algorithm (graph cut) along with a few other knowledge guided morphological operations to finalize the segmentation process. Based on OCT imaging data and its ground truth from the RETOUCH challenge, the proposed system achieves dice indices of 0.522, 0.682, and 0.612, and average absolute volume differences of 0.285, 0.115, and 0.156 mm$^3$ for intaretinal fluid, subretinal fluid, and pigment epithelial detachment respectively.
Tasks	Data Augmentation
Published	2017-08-17
URL	http://arxiv.org/abs/1708.05464v1
PDF	http://arxiv.org/pdf/1708.05464v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-detection-and-quantification-of
Repo
Framework

Gradient-enhanced kriging for high-dimensional problems


Title	Gradient-enhanced kriging for high-dimensional problems
Authors	Mohamed Amine Bouhlel, Joaquim R. R. A. Martins
Abstract	Surrogate models provide a low computational cost alternative to evaluating expensive functions. The construction of accurate surrogate models with large numbers of independent variables is currently prohibitive because it requires a large number of function evaluations. Gradient-enhanced kriging has the potential to reduce the number of function evaluations for the desired accuracy when efficient gradient computation, such as an adjoint method, is available. However, current gradient-enhanced kriging methods do not scale well with the number of sampling points due to the rapid growth in the size of the correlation matrix where new information is added for each sampling point in each direction of the design space. They do not scale well with the number of independent variables either due to the increase in the number of hyperparameters that needs to be estimated. To address this issue, we develop a new gradient-enhanced surrogate model approach that drastically reduced the number of hyperparameters through the use of the partial-least squares method that maintains accuracy. In addition, this method is able to control the size of the correlation matrix by adding only relevant points defined through the information provided by the partial-least squares method. To validate our method, we compare the global accuracy of the proposed method with conventional kriging surrogate models on two analytic functions with up to 100 dimensions, as well as engineering problems of varied complexity with up to 15 dimensions. We show that the proposed method requires fewer sampling points than conventional methods to obtain the desired accuracy, or provides more accuracy for a fixed budget of sampling points. In some cases, we get over 3 times more accurate models than a bench of surrogate models from the literature, and also over 3200 times faster than standard gradient-enhanced kriging models.
Tasks
Published	2017-08-08
URL	http://arxiv.org/abs/1708.02663v1
PDF	http://arxiv.org/pdf/1708.02663v1.pdf
PWC	https://paperswithcode.com/paper/gradient-enhanced-kriging-for-high
Repo
Framework

Multiple Context-Free Tree Grammars: Lexicalization and Characterization


Title	Multiple Context-Free Tree Grammars: Lexicalization and Characterization
Authors	Joost Engelfriet, Andreas Maletti, Sebastian Maneth
Abstract	Multiple (simple) context-free tree grammars are investigated, where “simple” means “linear and nondeleting”. Every multiple context-free tree grammar that is finitely ambiguous can be lexicalized; i.e., it can be transformed into an equivalent one (generating the same tree language) in which each rule of the grammar contains a lexical symbol. Due to this transformation, the rank of the nonterminals increases at most by 1, and the multiplicity (or fan-out) of the grammar increases at most by the maximal rank of the lexical symbols; in particular, the multiplicity does not increase when all lexical symbols have rank 0. Multiple context-free tree grammars have the same tree generating power as multi-component tree adjoining grammars (provided the latter can use a root-marker). Moreover, every multi-component tree adjoining grammar that is finitely ambiguous can be lexicalized. Multiple context-free tree grammars have the same string generating power as multiple context-free (string) grammars and polynomial time parsing algorithms. A tree language can be generated by a multiple context-free tree grammar if and only if it is the image of a regular tree language under a deterministic finite-copying macro tree transducer. Multiple context-free tree grammars can be used as a synchronous translation device.
Tasks
Published	2017-07-11
URL	http://arxiv.org/abs/1707.03457v1
PDF	http://arxiv.org/pdf/1707.03457v1.pdf
PWC	https://paperswithcode.com/paper/multiple-context-free-tree-grammars
Repo
Framework

A Neural-Symbolic Approach to Design of CAPTCHA


Title	A Neural-Symbolic Approach to Design of CAPTCHA
Authors	Qiuyuan Huang, Paul Smolensky, Xiaodong He, Li Deng, Dapeng Wu
Abstract	CAPTCHAs based on reading text are susceptible to machine-learning-based attacks due to recent significant advances in deep learning (DL). To address this, this paper promotes image/visual captioning based CAPTCHAs, which is robust against machine-learning-based attacks. To develop image/visual-captioning-based CAPTCHAs, this paper proposes a new image captioning architecture by exploiting tensor product representations (TPR), a structured neural-symbolic framework developed in cognitive science over the past 20 years, with the aim of integrating DL with explicit language structures and rules. We call it the Tensor Product Generation Network (TPGN). The key ideas of TPGN are: 1) unsupervised learning of role-unbinding vectors of words via a TPR-based deep neural network, and 2) integration of TPR with typical DL architectures including Long Short-Term Memory (LSTM) models. The novelty of our approach lies in its ability to generate a sentence and extract partial grammatical structure of the sentence by using role-unbinding vectors, which are obtained in an unsupervised manner. Experimental results demonstrate the effectiveness of the proposed approach.
Tasks	Image Captioning
Published	2017-10-29
URL	http://arxiv.org/abs/1710.11475v2
PDF	http://arxiv.org/pdf/1710.11475v2.pdf
PWC	https://paperswithcode.com/paper/a-neural-symbolic-approach-to-design-of
Repo
Framework

Human Action Recognition: Pose-based Attention draws focus to Hands


Title	Human Action Recognition: Pose-based Attention draws focus to Hands
Authors	Fabien Baradel, Christian Wolf, Julien Mille
Abstract	We propose a new spatio-temporal attention based mechanism for human action recognition able to automatically attend to the hands most involved into the studied action and detect the most discriminative moments in an action. Attention is handled in a recurrent manner employing Recurrent Neural Network (RNN) and is fully-differentiable. In contrast to standard soft-attention based mechanisms, our approach does not use the hidden RNN state as input to the attention model. Instead, attention distributions are extracted using external information: human articulated pose. We performed an extensive ablation study to show the strengths of this approach and we particularly studied the conditioning aspect of the attention mechanism. We evaluate the method on the largest currently available human action recognition dataset, NTU-RGB+D, and report state-of-the-art results. Other advantages of our model are certain aspects of explanability, as the spatial and temporal attention distributions at test time allow to study and verify on which parts of the input data the method focuses.
Tasks	Temporal Action Localization
Published	2017-12-20
URL	http://arxiv.org/abs/1712.08002v1
PDF	http://arxiv.org/pdf/1712.08002v1.pdf
PWC	https://paperswithcode.com/paper/human-action-recognition-pose-based-attention
Repo
Framework

Machine listening intelligence


Title	Machine listening intelligence
Authors	C. E. Cella
Abstract	This manifesto paper will introduce machine listening intelligence, an integrated research framework for acoustic and musical signals modelling, based on signal processing, deep learning and computational musicology.
Tasks
Published	2017-06-29
URL	http://arxiv.org/abs/1706.09557v1
PDF	http://arxiv.org/pdf/1706.09557v1.pdf
PWC	https://paperswithcode.com/paper/machine-listening-intelligence
Repo
Framework

An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns


Title	An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns
Authors	Vasily Morzhakov, Alexey Redozubov
Abstract	Cortical minicolumns are considered a model of cortical organization. Their function is still a source of research and not reflected properly in modern architecture of nets in algorithms of Artificial Intelligence. We assume its function and describe it in this article. Furthermore, we show how this proposal allows to construct a new architecture, that is not based on convolutional neural networks, test it on MNIST data and receive close to Convolutional Neural Network accuracy. We also show that the proposed architecture possesses an ability to train on a small quantity of samples. To achieve these results, we enable the minicolumns to remember context transformations.
Tasks
Published	2017-12-16
URL	http://arxiv.org/abs/1712.05954v1
PDF	http://arxiv.org/pdf/1712.05954v1.pdf
PWC	https://paperswithcode.com/paper/an-artificial-neural-network-architecture
Repo
Framework

Desensitized RDCA Subspaces for Compressive Privacy in Machine Learning


Title	Desensitized RDCA Subspaces for Compressive Privacy in Machine Learning
Authors	Artur Filipowicz, Thee Chanyaswad, S. Y. Kung
Abstract	The quest for better data analysis and artificial intelligence has lead to more and more data being collected and stored. As a consequence, more data are exposed to malicious entities. This paper examines the problem of privacy in machine learning for classification. We utilize the Ridge Discriminant Component Analysis (RDCA) to desensitize data with respect to a privacy label. Based on five experiments, we show that desensitization by RDCA can effectively protect privacy (i.e. low accuracy on the privacy label) with small loss in utility. On HAR and CMU Faces datasets, the use of desensitized data results in random guess level accuracies for privacy at a cost of 5.14% and 0.04%, on average, drop in the utility accuracies. For Semeion Handwritten Digit dataset, accuracies of the privacy-sensitive digits are almost zero, while the accuracies for the utility-relevant digits drop by 7.53% on average. This presents a promising solution to the problem of privacy in machine learning for classification.
Tasks
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07770v1
PDF	http://arxiv.org/pdf/1707.07770v1.pdf
PWC	https://paperswithcode.com/paper/desensitized-rdca-subspaces-for-compressive
Repo
Framework

Handwritten Bangla Digit Recognition Using Deep Learning


Title	Handwritten Bangla Digit Recognition Using Deep Learning
Authors	Md Zahangir Alom, Paheding Sidike, Tarek M. Taha, Vijayan K. Asari
Abstract	In spite of the advances in pattern recognition technology, Handwritten Bangla Character Recognition (HBCR) (such as alpha-numeric and special characters) remains largely unsolved due to the presence of many perplexing characters and excessive cursive in Bangla handwriting. Even the best existing recognizers do not lead to satisfactory performance for practical applications. To improve the performance of Handwritten Bangla Digit Recognition (HBDR), we herein present a new approach based on deep neural networks which have recently shown excellent performance in many pattern recognition and machine learning applications, but has not been throughly attempted for HBDR. We introduce Bangla digit recognition techniques based on Deep Belief Network (DBN), Convolutional Neural Networks (CNN), CNN with dropout, CNN with dropout and Gaussian filters, and CNN with dropout and Gabor filters. These networks have the advantage of extracting and using feature information, improving the recognition of two dimensional shapes with a high degree of invariance to translation, scaling and other pattern distortions. We systematically evaluated the performance of our method on publicly available Bangla numeral image database named CMATERdb 3.1.1. From experiments, we achieved 98.78% recognition rate using the proposed method: CNN with Gabor features and dropout, which outperforms the state-of-the-art algorithms for HDBR.
Tasks
Published	2017-05-07
URL	http://arxiv.org/abs/1705.02680v1
PDF	http://arxiv.org/pdf/1705.02680v1.pdf
PWC	https://paperswithcode.com/paper/handwritten-bangla-digit-recognition-using
Repo
Framework

TensorFlow Estimators: Managing Simplicity vs. Flexibility in High-Level Machine Learning Frameworks


Title	TensorFlow Estimators: Managing Simplicity vs. Flexibility in High-Level Machine Learning Frameworks
Authors	Heng-Tze Cheng, Zakaria Haque, Lichan Hong, Mustafa Ispir, Clemens Mewald, Illia Polosukhin, Georgios Roumpos, D Sculley, Jamie Smith, David Soergel, Yuan Tang, Philipp Tucker, Martin Wicke, Cassandra Xia, Jianwei Xie
Abstract	We present a framework for specifying, training, evaluating, and deploying machine learning models. Our focus is on simplifying cutting edge machine learning for practitioners in order to bring such technologies into production. Recognizing the fast evolution of the field of deep learning, we make no attempt to capture the design space of all possible model architectures in a domain- specific language (DSL) or similar configuration language. We allow users to write code to define their models, but provide abstractions that guide develop- ers to write models in ways conducive to productionization. We also provide a unifying Estimator interface, making it possible to write downstream infrastructure (e.g. distributed training, hyperparameter tuning) independent of the model implementation. We balance the competing demands for flexibility and simplicity by offering APIs at different levels of abstraction, making common model architectures available out of the box, while providing a library of utilities designed to speed up experimentation with model architectures. To make out of the box models flexible and usable across a wide range of problems, these canned Estimators are parameterized not only over traditional hyperparameters, but also using feature columns, a declarative specification describing how to interpret input data. We discuss our experience in using this framework in re- search and production environments, and show the impact on code health, maintainability, and development speed.
Tasks
Published	2017-08-08
URL	http://arxiv.org/abs/1708.02637v1
PDF	http://arxiv.org/pdf/1708.02637v1.pdf
PWC	https://paperswithcode.com/paper/tensorflow-estimators-managing-simplicity-vs
Repo
Framework

Stochastic Variance-reduced Gradient Descent for Low-rank Matrix Recovery from Linear Measurements


Title	Stochastic Variance-reduced Gradient Descent for Low-rank Matrix Recovery from Linear Measurements
Authors	Xiao Zhang, Lingxiao Wang, Quanquan Gu
Abstract	We study the problem of estimating low-rank matrices from linear measurements (a.k.a., matrix sensing) through nonconvex optimization. We propose an efficient stochastic variance reduced gradient descent algorithm to solve a nonconvex optimization problem of matrix sensing. Our algorithm is applicable to both noisy and noiseless settings. In the case with noisy observations, we prove that our algorithm converges to the unknown low-rank matrix at a linear rate up to the minimax optimal statistical error. And in the noiseless setting, our algorithm is guaranteed to linearly converge to the unknown low-rank matrix and achieves exact recovery with optimal sample complexity. Most notably, the overall computational complexity of our proposed algorithm, which is defined as the iteration complexity times per iteration time complexity, is lower than the state-of-the-art algorithms based on gradient descent. Experiments on synthetic data corroborate the superiority of the proposed algorithm over the state-of-the-art algorithms.
Tasks
Published	2017-01-02
URL	http://arxiv.org/abs/1701.00481v2
PDF	http://arxiv.org/pdf/1701.00481v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-variance-reduced-gradient-descent
Repo
Framework

NDT: Neual Decision Tree Towards Fully Functioned Neural Graph


Title	NDT: Neual Decision Tree Towards Fully Functioned Neural Graph
Authors	Han Xiao
Abstract	Though traditional algorithms could be embedded into neural architectures with the proposed principle of \cite{xiao2017hungarian}, the variables that only occur in the condition of branch could not be updated as a special case. To tackle this issue, we multiply the conditioned branches with Dirac symbol (i.e. $\mathbf{1}_{x>0}$), then approximate Dirac symbol with the continuous functions (e.g. $1 - e^{-\alphax}$). In this way, the gradients of condition-specific variables could be worked out in the back-propagation process, approximately, making a fully functioned neural graph. Within our novel principle, we propose the neural decision tree \textbf{(NDT)}, which takes simplified neural networks as decision function in each branch and employs complex neural networks to generate the output in each leaf. Extensive experiments verify our theoretical analysis and demonstrate the effectiveness of our model.
Tasks
Published	2017-12-16
URL	http://arxiv.org/abs/1712.05934v1
PDF	http://arxiv.org/pdf/1712.05934v1.pdf
PWC	https://paperswithcode.com/paper/ndt-neual-decision-tree-towards-fully
Repo
Framework