检索结果-内蒙古大学图书馆

Detection and recognition of food in photo galleries for analysis of user preferences 17th

学校读者我要写书评

暂无评论

Detection and recognition of food in photo galleries for an...

17th International Conference on Image analysis and Recognition, ICIAR 2020

作者： Miasnikov, Evgeniy Savchenko, Andrey St. Petersburg Department of Steklov Institute of Mathematics St. Petersburg Russia Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

ISBN: (纸本)9783030503468

Food analysis is one of the most important parts of user preference prediction engines for recommendation systems in the travel domain. In this paper, we describe and study the neural network method that allows you to recognize food in a gallery of photos taken with mobile devices. The described method consists of three main stages, including the classification of scenes, food detection, and subsequent classification. An essential feature of the developed method is the use of lightweight neural network models, which allows its usage on mobile devices. The development of the method was carried out using both known open data and a proprietary data set. © Springer Nature Switzerland AG 2020.

关键词： Convolutional neural networks

DEALING WITH SPARSE REWARDS USING GRAPH NEURAL networkS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gerasyov, Matvey Makarov, Ilya School of Data Analysis and Artificial Intelligence HSE University Moscow Russia Laboratory of Algorithms and Technologies for Network Analysis HSE University Nizhny Novgorod Russia AI Center NUST MISiS Moscow Russia Moscow Russia

Deep reinforcement learning in partially observable environments is a difficult task in itself and can be further complicated by a sparse reward signal. Most tasks involving navigation in three-dimensional environments provide the agent with minimal information. Typically, the agent receives a visual observation input from the environment and is rewarded once at the end of the episode. A good reward function could substantially improve the convergence of reinforcement learning algorithms for such tasks. The classic approach to increasing the density of the reward signal is to augment it with supplementary rewards. This technique is called reward shaping. In this study, we propose two modifications of one of the recent reward shaping methods based on graph convolutional networks: the first involving advanced aggregation functions, and the second utilizing the attention mechanism. We empirically validate the effectiveness of our solutions for the task of navigation in a 3D environment with sparse rewards. For the solution featuring the attention mechanism, we can also show that the learned attention is concentrated on edges corresponding to important transitions in the 3D environment. © 2022, CC BY-NC-ND.

关键词： Reinforcement learning

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

Journal of Global Optimization 2022年第3期88卷 591-651页

作者： Gribanov, Dmitry Shumilov, Ivan Malyshev, Dmitry Pardalos, Panos Laboratory of Algorithms and Technologies for Network Analysis HSE University Nizhny Novgorod Russian Federation Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russian Federation Department of Industrial and Systems Engineering University of Florida Gainesville USA

Many papers in the field of integer linear programming (ILP, for short) are devoted to problems of the type $$\max \{c^\top x :A x = b,\, x \in {{\,\mathrm{\mathbb {Z}}\,}}^n_{\ge 0}\}$$ , where all the entries of A, b, c are integer, parameterized by the number of rows of A and $$\Vert A\Vert _{\max }$$ . This class of problems is known under the name of ILP problems in the standard form, adding the word ”bounded” if $$x \le u$$ , 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 $$\begin{aligned} \max \{c^\top x :b_l \le A x \le b_r,\, x \in {{\,\mathrm{\mathbb {Z}}\,}}^n\}, \end{aligned}$$ where $$b_l$$ and $$b_r$$ 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 $$\Delta (A)$$ , where $$\Delta (A)$$ is the maximum of $$n \times n$$ 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 $$\Delta (A)$$ , 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 $$m \in \{0,1\}$$ . By this way, we give specialised sparsity, proximity, and complexity bounds for the problems on simplices, Knapsack problems and Subset-Sum problems.

关键词：

Discrete KP equation, generalized Volterra lattice and multiple orthogonal polynomials

学校读者我要写书评

暂无评论

Discrete KP equation, generalized Volterra lattice and multi...

International Conference on Orthogonal Polynomials,Integrable Systems and Their Applications on the Occasion of Prof. Mourad Ismails 70th Birthday(2014正交多项式国际会议)

作者： Valeriy A. Kalyagin National Research University Higher School of Economics Laboratory of Algorithms and technologies for Network AnalysisRussian

On the multi-stage shortest path problem under distributional uncertainty

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ketkov, Sergey S. Laboratory of Algorithms and Technologies for Networks Analysis HSE University Rodionova st. 136 Nizhny Novgorod603093 Russia

In this paper we consider an ambiguity-averse multi-stage network game between a user and an attacker. The arc costs are assumed to be random variables that satisfy prescribed first-order moment constraints for some subsets of arcs and individual probability constraints for some particular arcs. The user aims at minimizing its cumulative expected loss by traversing between two fixed nodes in the network, while the attacker’s objective is to maximize the user’s expected loss by selecting a distribution of arc costs from the family of admissible distributions. In contrast to most of the related studies, both the user and the attacker can dynamically adjust their decisions at particular nodes of the user’s path. By observing the user’s decisions, the attacker may reveal some additional distributional information associated with the arcs emanated from the current user’s position. It is shown that the resulting multi-stage distributionally robust shortest path problem (DRSPP) admits a linear mixed-integer programming reformulation (MIP). In particular, we distinguish between acyclic and general graphs by introducing different forms of non-anticipativity constraints. Finally, we perform a numerical study, where the quality of adaptive decisions and computational tractability of the proposed MIP reformulation are explored with respect to several classes of synthetic network instances. © 2022, CC BY-NC-ND.

关键词： Graph theory

A quasi-energy function for Pixton diffeomorphisms defined by generalized Mazur knots

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Medvedev, Timur Pochinka, Olga Laboratory of Algorithms and Technologies for Network Analysis HSE University 136 Rodionova Street Niznhy Novgorod Russia International Laboratory of Dynamical Systems and Applications HSE University 25/12 Bolshaya Pecherckaya Street Niznhy Novgorod Russia

In this paper we give a lower estimate for the number of critical points of the Lyapunov function for Pixton diffeomorphisms (i.e. Morse-Smale diffeomorphisms in dimension 3 whose chain recurrent set consists of four points: one source, one saddle and two sinks). Ch. Bonatti and V. Grines proved that the class of topological equivalence of such diffeomorphism f is completely defined by the equivalency class of the Hopf knot Lf that is the knot in the generating class of the fundamental group of the manifold S2 × S1. They also proved that there are infinitely many such classes and that any Hopf knot can be realized by a Pixton diffeomorphism. D. Pixton proved that diffeomorphisms defined by the standard Hopf knot L0 = {s} × S1 have an energy function (Lyapunov function) whose set of critical points coincide with the chain recurrent set whereas the set of critical points of any Lyapunov function for Pixton diffeomorphism with nontrivial (i.e. non equivalent to the standard) Hopf knot is strictly larger than the chain recurrent set of the diffeomorphism. The Lyapunov function for Pixton diffeomorphism with minimal number of critical points is called the quasi-energy function. In this paper we construct a quasi-energy function for Pixton diffeomorphisms defined by a generalized Mazur *** Codes 37C15, 37D15 © 2023, CC BY.

关键词： Lyapunov functions

Optimization of Gain in Symmetrized Itakura-Saito Discrimination for Pronunciation Learning 19th

学校读者我要写书评

暂无评论

Optimization of Gain in Symmetrized Itakura-Saito Discrimina...

19th International Conference on Mathematical Optimization Theory and Operations Research, MOTOR 2020

作者： Savchenko, Andrey V. Savchenko, Vladimir V. Savchenko, Lyudmila V. Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia Nizhny Novgorod State Linguistic University Nizhny Novgorod Russia Department of Information Systems and Technologies National Research University Higher School of Economics Nizhny Novgorod Russia

ISBN: (纸本)9783030499877

This paper considers an assessment and evaluation of the pronunciation quality in computer-aided language learning systems. We propose the novel distortion measure for speech processing by using the gain optimization of the symmetrized Itakura-Saito divergence. This dissimilarity is implemented in a complete algorithm for pronunciation learning and improvement. At its first stage, a user has to achieve a stable pronunciation of all sounds by matching them with sounds of an ideal speaker. At the second stage, the recognition of sounds and their short sequences is carried out to guarantee the distinguishability of learned sounds. The training set may contain not only ideal sounds but the best utterances of a user obtained at the previous step. Finally, the word recognition accuracy is estimated by using deep neural networks fine-tuned on the best words from a user. Experimental study shows that the proposed procedure makes it possible to achieve high efficiency for learning of sounds and their sequences even in the presence of noise in an observed utterance. © 2020, Springer Nature Switzerland AG.

关键词： Convolutional neural networks

Models, algorithms and technologies for network analysis 1

学校读者我要写书评

暂无评论

丛书名： Springer Proceedings in Mathematics & Statistics

1000年

作者： Valery A. Kalyagin Petr A. Koldanov Panos M. Pardalos

ISBN: (数字)9783319296081

ISBN: (纸本)9783319296067;9783319806075

The contributions in this volume cover a broad range of topics including maximum cliques, graph coloring, data mining, brain networks, Steiner forest, logistic and supply chain networks. network algorithms and their applications to market graphs, manufacturing problems, internet networks and social networks are highlighted. The "Fourth International Conference in network analysis," held at the Higher School of Economics, Nizhny Novgorod in May 2014, initiated joint research between scientists, engineers and researchers from academia, industry and government; the major results of conference participants have been reviewed and collected in this Work. Researchers and students in mathematics, economics, statistics, computer science and engineering will find this collection a valuable resource filled with the latest research in network analysis.

关键词： algorithms Combinatorics Operations Research, Management Science

Dota Underlords Game Is NP-Complete

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ponomarenko, Alexander A. Sirotkin, Dmitry V. Laboratory of Algorithms and Technologies for Network Analysis National Research University Higher School of Economics Nizhny Novgorod Russia

In this paper, we demonstrate how the problem of the optimal team choice in the popular computer game Dota Underlords can be reduced to the problem of linear integer programming. We propose a model and solve it for the real data. We also prove that this problem belongs to the NP-complete class and show that it reduces to the maximum edge weighted clique problem. Copyright © 2020, The Authors. All rights reserved.

关键词： Computer games