Design and analysis of neural networks for systems optimization

Detalhes bibliográficos
Autor(a) principal: da Silva, Ivan N.
Data de Publicação: 1999
Outros Autores: Bordon, Mario E., de Souza, Andre N.
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://hdl.handle.net/11449/219223
Resumo: Artificial neural networks are dynamic systems consisting of highly interconnected and parallel nonlinear processing elements that are shown to be extremely effective in computation. This paper presents an architecture of artificial neural networks that can be used to solve several classes of optimization problems. More specifically, a modified Hopfield network is developed and its internal parameters are computed using the valid-subspace technique. Among the problems that can be treated by the proposed approach include combinatorial optimization problems and dynamic programming problems.
id UNSP_397de8b16f5475249f864a5d7249dc77
oai_identifier_str oai:repositorio.unesp.br:11449/219223
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Design and analysis of neural networks for systems optimizationArtificial neural networks are dynamic systems consisting of highly interconnected and parallel nonlinear processing elements that are shown to be extremely effective in computation. This paper presents an architecture of artificial neural networks that can be used to solve several classes of optimization problems. More specifically, a modified Hopfield network is developed and its internal parameters are computed using the valid-subspace technique. Among the problems that can be treated by the proposed approach include combinatorial optimization problems and dynamic programming problems.State Univ of Sao Paulo, BauruState Univ of Sao Pauloda Silva, Ivan N.Bordon, Mario E.de Souza, Andre N.2022-04-28T18:54:27Z2022-04-28T18:54:27Z1999-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject684-689Proceedings of the International Joint Conference on Neural Networks, v. 1, p. 684-689.http://hdl.handle.net/11449/2192232-s2.0-0033333587Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings of the International Joint Conference on Neural Networksinfo:eu-repo/semantics/openAccess2022-04-28T18:54:27Zoai:repositorio.unesp.br:11449/219223Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462022-04-28T18:54:27Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Design and analysis of neural networks for systems optimization
title Design and analysis of neural networks for systems optimization
spellingShingle Design and analysis of neural networks for systems optimization
da Silva, Ivan N.
title_short Design and analysis of neural networks for systems optimization
title_full Design and analysis of neural networks for systems optimization
title_fullStr Design and analysis of neural networks for systems optimization
title_full_unstemmed Design and analysis of neural networks for systems optimization
title_sort Design and analysis of neural networks for systems optimization
author da Silva, Ivan N.
author_facet da Silva, Ivan N.
Bordon, Mario E.
de Souza, Andre N.
author_role author
author2 Bordon, Mario E.
de Souza, Andre N.
author2_role author
author
dc.contributor.none.fl_str_mv State Univ of Sao Paulo
dc.contributor.author.fl_str_mv da Silva, Ivan N.
Bordon, Mario E.
de Souza, Andre N.
description Artificial neural networks are dynamic systems consisting of highly interconnected and parallel nonlinear processing elements that are shown to be extremely effective in computation. This paper presents an architecture of artificial neural networks that can be used to solve several classes of optimization problems. More specifically, a modified Hopfield network is developed and its internal parameters are computed using the valid-subspace technique. Among the problems that can be treated by the proposed approach include combinatorial optimization problems and dynamic programming problems.
publishDate 1999
dc.date.none.fl_str_mv 1999-12-01
2022-04-28T18:54:27Z
2022-04-28T18:54:27Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv Proceedings of the International Joint Conference on Neural Networks, v. 1, p. 684-689.
http://hdl.handle.net/11449/219223
2-s2.0-0033333587
identifier_str_mv Proceedings of the International Joint Conference on Neural Networks, v. 1, p. 684-689.
2-s2.0-0033333587
url http://hdl.handle.net/11449/219223
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Proceedings of the International Joint Conference on Neural Networks
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 684-689
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1799964397548863488

Registros relacionados