检索结果-内蒙古大学图书馆

Probabilistic Neural network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Savchenko, Andrey V. Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics 25/12 Bolshaya Pecherskaya St. Nizhny Novgorod603155 Russia

— If the training dataset is not very large, image recognition is usually implemented with the transfer learning methods. In these methods the features are extracted using a deep convolutional neural network, which was preliminarily trained with an external very-large dataset. In this paper we consider the nonparametric classification of extracted feature vectors with the probabilistic neural network (PNN). The number of neurons at the pattern layer of the PNN is equal to the database size, which causes the low recognition performance and high memory space complexity of this network. We propose to overcome these drawbacks by replacing the exponential activation function in the Gaussian Parzen kernel to the complex exponential functions in the Fejér kernel. We demonstrate that in this case it is possible to implement the network with the number of neurons in the pattern layer proportional to the cubic root of the database size. Thus, the proposed modification of the PNN makes it possible to significantly decrease runtime and memory complexities without loosing its main advantages, namely, extremely fast training procedure and the convergence to the optimal Bayesian decision. An experimental study in visual object category classification and unconstrained face recognition with contemporary deep neural networks have shown, that our approach obtains very efficient and rather accurate decisions for the small training sample in comparison with the well-known classifiers. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

Automatic Privacy Detection in Scanned Document Images Based on Deep Neural networks

学校读者我要写书评

暂无评论

Automatic Privacy Detection in Scanned Document Images Based...

International Russian Automation Conference (RusAutoCon)

作者： Lyudmila Kopeykina Andrey V. Savchenko National Research University Higher School of Economics Nizhny Novgorod Russia Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

The authors consider the problem of automatic detection of private scanned documents based on text recognition with deep neural networks. The paper suggests implementing a two-phase approach with the first stage which includes efficient EAST text detection and recognition using Tesseract OCR Engine. Secondly, the authors classify the privacy of a scanned document by deep neural networks applied to the extracted text. After that, a special dataset is gathered in order to train these networks. The experiments show that using OCR Engine for both text detection and segmentation ends up with relatively poor identification of private documents when compared to preliminary text detection with EAST method. Moreover, conventional keyword spotting using the list of sensitive words is less accurate when compared to neural network-based methods. Finally, it was demonstrated that the classification of a bag of most frequent words outperforms traditional text classification techniques with LSTM and convolutional networks.

关键词： Text recognition Neural networks Detectors Privacy Task analysis Automation Optical character recognition software

Group-level emotion recognition using transfer learning from face identification

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Rassadin, Alexandr Gruzdev, Alexey Savchenko, Andrey National Research University Higher School of Economics Laboratory of Algorithms and Technologies for Network Analysis Nizhny Novgorod Russia National Research University Higher School of Economics Nizhny Novgorod Russia

In this paper we describe our algorithmic approach, which was used for submissions in the fifth Emotion Recognition in the Wild (EmotiW 2017) group-level emotion recognition sub-challenge. We extracted feature vectors of detected faces using the Convolutional Neural network trained for face identification task, rather than traditional pre-training on emotion recognition problems. In the final pipeline an ensemble of Random Forest classifiers was learned to predict emotion score using available training set. In case when the faces have not been detected, one member of our ensemble extracts features from the whole image. During our experimental study, the proposed approach showed the lowest error rate when compared to other explored techniques. In particular, we achieved 75.4% accuracy on the validation data, which is 20% higher than the handcrafted feature-based baseline. The source code using Keras framework is publicly available.68T10, 68T45 Copyright © 2017, The Authors. All rights reserved.

关键词： Speech recognition

Improving the Accuracy of One-Shot Detectors for Small Objects in X-ray Images

学校读者我要写书评

暂无评论

Improving the Accuracy of One-Shot Detectors for Small Objec...

International Russian Automation Conference (RusAutoCon)

作者： Polina Demochkina Andrey V. Savchenko National Research University Higher School of Economics Nizhny Novgorod Russia Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

The following topics are dealt with: control engineering computing; control system synthesis; optimisation; process control; electric drives; nonlinear control systems; motion control; machine control; production engi... 详细信息

ISBN: (数字)9781728161303

ISBN: (纸本)9781728161310

关键词： X-ray imaging Detectors Object detection Training Inspection Automation Weapons

Faster algorithms for Sparse ILP and Hypergraph Multi-Packing/Multi-Cover Problems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gribanov, Dmitry Malyshev, Dmitry Zolotykh, Nikolai Shumilov, Ivan Laboratory of Algorithms and Technologies for Network Analysis HSE University 136 Rodionova Ulitsa Nizhny Novgorod603093 Russia Lobachevsky State University of Nizhny Novgorod 23 Gagarina Avenue Nizhny Novgorod603950 Russia Mathematics of Future Technologies Center Lobachevsky State University of Nizhni Novgorod 23 Gagarina Avenue Nizhny Novgorod603950 Russia

In our paper, we consider the following general problems: check feasibility, count the number of feasible solutions, find an optimal solution, and count the number of optimal solutions in P ∩ Zn, assuming that P is a polyhedron, defined by systems Ax ≤ b or Ax = b, x ≥ 0 with a sparse matrix A. We develop algorithms for these problems that outperform state of the art ILP and counting algorithms on sparse instances with bounded elements. We use known and new methods to develop new exponential algorithms for Edge/Vertex Multi-Packing/Multi-Cover Problems on graphs and hypergraphs. This framework consists of many different problems, such as the Stable Multi-set, Vertex Multi-cover, Dominating Multi-set, Set Multi-cover, Multi-set Multi-cover, and Hypergraph Multi-matching problems, which are natural generalizations of the standard Stable Set, Vertex Cover, Dominating Set, Set Cover, and Maximum Matching problems. Copyright © 2022, The Authors. All rights reserved.

关键词： Optimal systems

On a numerically stable algorithm for the analysis of Generalized Volterra lattice

学校读者我要写书评

暂无评论

On a numerically stable algorithm for the analysis of Genera...

作者： Kalyagin, Valery Sokolov, Maxim Laboratory of Algorithms and Technologies for Network Analysis Department of Applied Mathematics and Informatics The National Research University Higher School of Economics 136 Rodionova Street Nizhny Novgorod Russian Federation 603093 Russia MERA Ltd and Department of Applied Mathematics and Informatics National Research University Higher School of Economics Bol'shaya Pechërskaya Street 25/12 Nizhny Novgorod Russian Federation 603155 Russia

ISBN: (纸本)9781461455738

Volterra or Langmuir lattice is the dynamical model where the interaction of particle with the nearest neighbors is taken into account. It is known since J. Moser that the analysis of the Volterra lattice is related with isospectral deformation of a tridiagonal Jacobi operator. The main numerical problem in this setting is the inverse spectral problem for this Jacobi operator. Generalized Volterra lattice is a dynamical model where the interaction of particle with some fixed number of neighbors is taken into account. This model is a particular case of the discrete KP equation. The analysis of discrete KP equation is related with a class of Hessenberg operators. In this chapter we propose and study a stable algorithm for the numerical solution of the inverse spectral problem for the band Hessenberg operator with application to the analysis of generalized Volterra lattice. © Springer Science+Business Media New York 2013.

关键词： Inverse problems

On ∆-Modular Integer Linear Problems In The Canonical Form And Equivalent Problems

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gribanov, Dmitry Shumilov, Ivan Malyshev, Dmitry Pardalos, Panos Laboratory of Algorithms and Technologies for Network Analysis HSE University 136 Rodionova Ulitsa Nizhny Novgorod603093 Russia Lobachevsky State University of Nizhny Novgorod 23 Gagarina Avenue Nizhny Novgorod603950 Russia Department of Industrial and Systems Engineering University of Florida 401 Weil Hall GainesvilleFL116595 United States

Many papers in the field of integer linear programming (ILP, for short) are devoted to problems of the type max{cx: Ax = b, x ∈ Zn≥0}, where all the entries of A, b, c are integer, parameterized by the number of rows of A and kAkmax. This class of problems is known under the name of ILP problems in the standard form, adding the word"bounded" if x ≤ u, for some integer vector u. Recently, many new sparsity, proximity, and complexity results were obtained for bounded and unbounded ILP problems in the standard form. In this paper, we consider ILP problems in the canonical form max{cx: bl ≤ Ax ≤ br, x ∈ Zn}, where bl and br are integer vectors. We assume that the integer matrix A has the rank n, (n + m) rows, n columns, and parameterize the problem by m and ∆(A), where ∆(A) is the maximum of n × n sub-determinants of A, taken in the absolute value. We show that any ILP problem in the standard form can be polynomially reduced to some ILP problem in the canonical form, preserving m and ∆(A), but the reverse reduction is not always possible. More precisely, we define the class of generalized ILP problems in the standard form, which includes an additional group constraint, and prove the equivalence to ILP problems in the canonical form. We generalize known sparsity, proximity, and complexity bounds for ILP problems in the canonical form. Additionally, sometimes, we strengthen previously known results for ILP problems in the canonical form, and, sometimes, we give shorter proofs. Finally, we consider the special cases of m ∈ {0, 1}. By this way, we give specialised sparsity, proximity, and complexity bounds for the problems on simplices, Knapsack problems and Subset-Sum problems. Copyright © 2020, The Authors. All rights reserved.

关键词： Equivalence classes

Surface waves prediction based on long-range acoustic backscattering in a mid-frequency range

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ermoshkin, Alexey V. Kosteev, Dmitry A. Ponomarenko, Alexander A. Razumov, Dmitry D. Salin, Mikhail B. Center for Hydroacoustics and Geophysical Research Division Institute of Applied Physics The Russian Academy of Sciences Nizhny Novgorod603950 Russia Laboratory of Algorithm and Technologies for Network Analysis HSE University Nizhny Novgorod603036 Russia

New data was obtained for a frequency band that had not been so well-studied for sea surface probing applications before. During the described 2-weeks sea experiment 1-3 kHz tonal pulses were emitted from a platform, located on the northern Black Sea shelf, and Doppler spectrum of reverberation was studied. We believe that this band is worth further studying due the sound propagation range is large enough to meet practical needs in coastal zone while the angle-distance resolution is quite moderate. However it is quite difficult to interpret the obtained data since backscattering spectrum shape is influenced by a series of effects and has a complicated link to wind waves and currents parameters. Backscattering of acoustical signals was received for distances around 2 nautical miles. Significant wave height, dominant wave frequency were estimated as the result of such signals processing with the use of machine learning tools. A decision-tree-based mathematical regression model was trained to solve the inverse problem. Wind waves prediction is in a good agreement with direct measurements, made on the platform, and machine learning results allow physical interpretation. Copyright © 2022, The Authors. All rights reserved.

关键词： Surface waves

Neural networks compression for language modeling

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Grachev, Artem M. Ignatov, Dmitry I. Savchenko, Andrey V. Samsung RandD Institute Rus Moscow Russia National Research University Higher School of Economics Moscow Russia National Research University Higher School of Economics Laboratory of Algorithms and Technologies for Network Analysis Nizhny Novgorod Russia

In this paper, we consider several compression techniques for the language modeling problem based on recurrent neural networks (RNNs). It is known that conventional RNNs, e.g, LSTM-based networks in language modeling, are characterized with either high space complex- ity or substantial inference time. This problem is especially crucial for mobile applications, in which the constant interaction with the remote server is inappropriate. By using the Penn Treebank (PTB) dataset we compare pruning, quantization, low-rank factorization, tensor train decomposition for LSTM networks in terms of model size and suitability for fast inference.62M45, 68T50 Copyright © 2017, The Authors. All rights reserved.

关键词： Factorization