检索结果-内蒙古大学图书馆

Using a Saliency-Driven Convolutional Neural Network Framework for Brain Tumor Detection 22

学校读者我要写书评

暂无评论

Using a Saliency-Driven Convolutional Neural Network Framewo...

6th International Conference on Medical and Health Informatics, ICMHI 2022

作者： Oliveira, Paulo Henrique De C. Farias, Mylène C.Q. Ferreira, Daniel S. Krylov, Andrey S. Ding, Yong Department of Electrical Engineering University of Brasilia Brasília DF Brazil Department of Computing Science Instituto Federal de Education Ciencia e Tecnologia Do Ceara CE Fortaleza Brazil Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Moscow Russia College of Information Science and Electronic Engineering Zhejiang University Zhejiang China

ISBN: (纸本)9781450396301

The process of diagnosing brain tumors from magnetic resonance imaging (MRI) is often time-consuming. Thus, a rapid analyses through an automated system could help improve the treatment possibilities and optimize hospital resources. This paper proposes a method for the classification of brain tumors by means of pre-selecting the tumor region. We estimate the region of interest using attention algorithms and input it to a neural network that classifies the regions as tumoral and non-tumoral. Pre-selecting the region of interest, instead of using the entire image, produced a final classification accuracy of 91.68%, 92.58%, 92.69%, and 93.4% with the models Resnet18, Resnet34, VGG16, and Alexnet, respectively. Once the dimensional space of the input image is reduced, the neural networks is able to capture additional details of the tumor regions during the training stage. This study demonstrates the importance of saliency maps for identifying tumor regions in magnetic resonance images. © 2022 ACM.

关键词： Magnetic resonance imaging

Reinforcement-learning-based Algorithms for Optimization Problems and Applications to Inverse Problems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Chen Zhao, Yun-Bin Lu, Zhipeng Zhang, Ye Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Shenzhen Research Institute of Big Data Chinese University of Hong Kong Shenzhen China Faculty of Computational Mathematics and Cybernetics Shenzhen MSU-BIT University Shenzhen518172 China School of Mathematics and Statistics Beijing Institute of Technology Beijing100081 China

We design a new iterative algorithm, called REINFORCE-OPT, for solving a general type of optimization problems. This algorithm parameterizes the solution search rule and iteratively updates the parameter using a reinforcement learning (RL) algorithm resembling REINFORCE. To gain a deeper understanding of the RL-based methods, we show that REINFORCE-OPT essentially solves a stochastic version of the given optimization problem, and that under standard assumptions, the searching rule parameter almost surely converges to a locally optimal value. Experiments show that REINFORCE-OPT outperforms other optimization methods such as gradient descent, the genetic algorithm, and particle swarm optimization, via its ability to escape from locally optimal solutions and its robustness to the choice of initial values. With rigorous derivations, we formally introduce the use of reinforcement learning to deal with inverse problems. By choosing specific probability models for the action-selection rule, we can also connect our approach to the conventional methods of Tikhonov regularization and iterative regularization. We take non-linear integral equations and parameter-identification problems in partial differential equations as examples to show how reinforcement learning can be applied in solving non-linear inverse problems. The numerical experiments highlight the strong performance of REINFORCE-OPT, as well as its ability to quantify uncertainty in error estimates and identify multiple solutions for ill-posed inverse problems that lack solution stability and *** Codes 90C26, 65J22, 65J20, 90C40, 90C15, 45Q05, 47A52 Copyright © 2023, The Authors. All rights reserved.

关键词： Optimization algorithms

FIESTA5: Numerical high-performance Feynman integral evaluation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Smirnov, Alexander V. Shapurov, N.D. Vysotsky, L.I. Research Computing Center Moscow State University Moscow Russia Faculty of Computational Mathematics and Cybernetics Moscow State University Moscow Russia Moscow Center for Fundamental and Applied Mathematics Moscow Russia

In this paper we present a new release of the FIESTA program (Feynman Integral Evaluation by a Sector decomposiTion Approach). FIESTA5 is performance-oriented — we implemented improvements of various kinds in order to make Feynman integral evaluation faster. We plugged in two new integrators, the Quasi Monte Carlo and Tensor Train. At the same time the old code of FIESTA4 was upgraded to the C++17 standard and mostly rewritten without self-made structures such as hash tables. There are also several essential improvements which are most relevant for complex integrations — the new release is capable of producing results where previously impossible. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum theory

Tensor-train numerical integration of multivariate functions with singularities

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Vysotsky, Lev I. Smirnov, Alexander V. Tyrtyshnikov, Eugene E. HSE University Russia Faculty of Computational Mathematics and Cybernetics Moscow State University Russia Moscow Center for Fundamental and Applied Mathematics Russia Research Computing Center Moscow State University Russia Marchuk Institute of Numerical Mathematics Russian Academy of Sciences Russia

Numerical integration is a classical problem emerging in many fields of science. Multivariate integration cannot be approached with classical methods due to the exponential growth of the number of quadrature nodes. We propose a method to overcome this problem. Tensor-train decomposition of a tensor approximating the integrand is constructed and used to evaluate a multivariate quadrature formula. We show how to deal with singularities in the integration domain and conduct theoretical analysis of the integration accuracy. The reference open-source implementation is *** Codes 26B15, 15A69 © 2021, CC BY.

关键词： Tensors

Supercomputer efficiency: Complex approach inspired by lomonosov-2 history evaluation 4th

学校读者我要写书评

暂无评论

Supercomputer efficiency: Complex approach inspired by lomon...

4th Russian Supercomputing Days Conference, RuSCDays 2018

作者： Leonenkov, Sergei Zhumatiy, Sergey Research Computing Center Lomonosov Moscow State University Moscow Russia Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Moscow Russia

ISBN: (纸本)9783030058067

These days the number of supercomputer users and the jobs they execute is rapidly growing, especially for supercomputers, providing computing time to external users. Supercomputers and their computing time are highly expensive, so their efficiency is crucial for both users and owners. There are several ways to increase operational efficiency, however, in most cases it involves a trade-off between efficiency metrics. This brings about a need to define "efficiency" in each specific case. We use the historical data from two largest Russian supercomputers to create a number of metrics in order to provide the definition of resource management "efficiency". The data from both Lomonosov and Lomonosov-2 supercomputers consists of over one year history of job executions. Lomonosov and Lomonosov-2 efficiency in terms of CPU hours utilization is considerably high, nevertheless, our global goal is to offer the way to maintain or improve this metric when maximizing others examined in the paper. © 2019, Springer Nature Switzerland AG.

关键词： Supercomputers

An Approach for Analyzing Influence Factors on Performance of Implementations of Standard Algorithms

学校读者我要写书评

暂无评论

An Approach for Analyzing Influence Factors on Performance o...

2019 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2019

作者： Zheltkov, Artem Nikitenko, Dmitry Lomonosov Moscow State University Faculty of Computation Mathematics and Cybernetics Moscow Russia Research Computing Center Lomonosov Moscow State University Moscow Russia

ISBN: (纸本)9781728144016

This paper illustrates the approach for inspecting factors of hardware details and computing problems that impact the performance of typical computing applications and for estimating its influence. The approach extends the idea of supercomputing lists (like TOP500, Graph500, HPCG and others) and combines it with researching algorithms properties (given by AlgoWiki). Possible applications of the approach are described and the main principles of the implementation are given. © 2019 IEEE.

关键词： Benchmarking

Active exploration for body model learning through self-touch on a humanoid robot with artificial skin

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gama, Filipe Shcherban, Maksym Rolf, Matthias Hoffmann, Matej Department of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic School of Engineering Computing and Mathematics Oxford Brookes University Oxford United Kingdom

The mechanisms of infant development are far from understood. Learning about one’s own body is likely a foundation for subsequent development. Here we look specifically at the problem of how spontaneous touches to the body in early infancy may give rise to first body models and bootstrap further development such as reaching competence. Unlike visually elicited reaching, reaching to own body requires connections of the tactile and motor space only, bypassing vision. Still, the problems of high dimensionality and redundancy of the motor system persist. In this work, we present an embodied computational model on a simulated humanoid robot with artificial sensitive skin on large areas of its body. The robot should autonomously develop the capacity to reach for every tactile sensor on its body. To do this efficiently, we employ the computational framework of intrinsic motivations and variants of goal babbling—as opposed to motor babbling—that prove to make the exploration process faster and alleviate the ill-posedness of learning inverse kinematics. Based on our results, we discuss the next steps in relation to infant studies: what information will be necessary to further ground this computational model in behavioral data. Copyright © 2020, The Authors. All rights reserved.

关键词： Anthropomorphic robots

Erratum to: Expanded Personality as the Main Entity and Subject of Philosophical Analysis: Implications for Education

学校读者我要写书评

暂无评论

Doklady mathematics 2024年第1期109卷 100-100页

作者： Semenov, A. L. Ziskin, K. E. Faculty of Mechanics and Mathematics Moscow State University Moscow Russia Axel Berg Institute of Cybernetics and Educational Computing Federal Research Center “Computer Science and Control” Russian Academy of Sciences Moscow Russia National Research University Higher School of Economics Moscow Russia Autonomous Nonprofit Organization of Additional Professional Education Higher School of Economics Moscow Russia

An Erratum to this paper has been published: https://***/10.1134/S1064562424010010

关键词：

Parallel structure of algorithms and training computational technology specialists

学校读者我要写书评

暂无评论

Parallel structure of algorithms and training computational ...

International Scientific Conference on Informatics 2018: Problems, Methodologies and Technologies, IPMT 2018

作者： Antonov, A.S. Voevodin, V.V. Popova, N.N. Research Computing Center Lomonosov Moscow State University Leninskie gory bld. 4 Moscow119234 Russia Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Leninskie gory bld. 52 Moscow119991 Russia

A universal method for describing an algorithm's parallel structure was developed as a part of AlgoWiki Open Encyclopedia of Parallel Algorithmic Features. AlgoWiki is not just an important source of information on specific algorithms, but also a good training ground for students. To develop a high-quality algorithm description, one needs to study its structure, identify its key properties, obtain the data by practical experiments on a supercomputer and learn to visualize the results. This article describes the experience of conducting a computer lab course on parallel algorithm structure at the faculty of Computational mathematics and cybernetics at Lomonosov Moscow State University. © Published under licence by IOP Publishing Ltd.

关键词： Supercomputers