Logo BSU

Please use this identifier to cite or link to this item: http://elib.bsu.by/handle/123456789/120215
Title: Mathematical models of complex systems on the basis of artificial neural networks
Authors: Vasilyev, A. N.
Tarkhov, D. A.
Keywords: ЭБ БГУ::ТЕХНИЧЕСКИЕ И ПРИКЛАДНЫЕ НАУКИ. ОТРАСЛИ ЭКОНОМИКИ::Автоматика. Вычислительная техника
Issue Date: 2014
Publisher: Minsk : Education and Upbringing
Citation: Nonlinear Phenomena in Complex Systems. - 2014. - Vol. 17, N 3. - P. 327-335
Abstract: Neural networking technique with models based on ordinary/partial differential equations is applied to the known incorrect problems. Solutions to such problems by routine approaches are difficult. The problem approximate solution is found as the artificial neural network output with a prescribed architecture. Network weights are determined in the stepwise network training based on the error functional minimization process in general. The case of the system parameters given in some variation intervals and the parameter set as a part of input data is considered. The construction of robust parameter neural network models is examined using some problems in classical and non-classical statements. The direct problem solution and the inverse problem regularization for the offered neural network approach are constructed uniformly. The neurocomputing results for fixed and growing neural networks are given. The supercomputer use is discussed. The neural network approach advantages and some possible generalizations are mentioned.
URI: http://elib.bsu.by/handle/123456789/120215
ISSN: 1561 - 4085
Appears in Collections:2014. Volume 17. Number 3

Files in This Item:
File Description SizeFormat 
v17no3p327.pdf128,68 kBAdobe PDFView/Open


PlumX

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.