Development of neurofuzzy architecture for solving the N-Queens problem
Autor(a) principal: | |
---|---|
Data de Publicação: | 2005 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1080/03081070500422695 http://hdl.handle.net/11449/224676 |
Resumo: | 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 recurrent neural networks for solving the N -Queens problem. More specifically, a modified Hopfield network is developed and its internal parameters are explicitly computed using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points, which represent a solution of the considered problem. The network is shown to be completely stable and globally convergent to the solutions of the N -Queens problem. A fuzzy logic controller is also incorporated in the network to minimize convergence time. Simulation results are presented to validate the proposed approach. |
id |
UNSP_768bdb4738586260a6c257d367bbb03d |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/224676 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Development of neurofuzzy architecture for solving the N-Queens problemCombinatorial optimizationFuzzy inference systemsHopfield networkNeural network architectureRecurrent neural networkNeural 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 recurrent neural networks for solving the N -Queens problem. More specifically, a modified Hopfield network is developed and its internal parameters are explicitly computed using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points, which represent a solution of the considered problem. The network is shown to be completely stable and globally convergent to the solutions of the N -Queens problem. A fuzzy logic controller is also incorporated in the network to minimize convergence time. Simulation results are presented to validate the proposed approach.Department of Electrical Engineering State University of São Paulo-UNESP UNESP/FE/DEE, CP 473, CEP 17033-360, Bauru, SPUniversity of São Paulo (USP)São Paulo State University (UNESP)State University of Sao Paulo (UNESP)Department of Electrical Engineering State University of São Paulo-UNESP UNESP/FE/DEE, CP 473, CEP 17033-360, Bauru, SPSão Paulo State University (UNESP)State University of Sao Paulo (UNESP)Universidade Estadual Paulista (UNESP)Universidade de São Paulo (USP)Da Silva, Ivan Nunes [UNESP]Ulson, Jose Alfredo [UNESP]De Souza, Andre Nunes [UNESP]2022-04-28T20:06:51Z2022-04-28T20:06:51Z2005-11-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article717-734http://dx.doi.org/10.1080/03081070500422695International Journal of General Systems, v. 34, n. 6, p. 717-734, 2005.0308-10791563-5104http://hdl.handle.net/11449/22467610.1080/030810705004226952-s2.0-30344469712Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengInternational Journal of General Systemsinfo:eu-repo/semantics/openAccess2022-04-28T20:06:51Zoai:repositorio.unesp.br:11449/224676Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462022-04-28T20:06:51Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Development of neurofuzzy architecture for solving the N-Queens problem |
title |
Development of neurofuzzy architecture for solving the N-Queens problem |
spellingShingle |
Development of neurofuzzy architecture for solving the N-Queens problem Da Silva, Ivan Nunes [UNESP] Combinatorial optimization Fuzzy inference systems Hopfield network Neural network architecture Recurrent neural network |
title_short |
Development of neurofuzzy architecture for solving the N-Queens problem |
title_full |
Development of neurofuzzy architecture for solving the N-Queens problem |
title_fullStr |
Development of neurofuzzy architecture for solving the N-Queens problem |
title_full_unstemmed |
Development of neurofuzzy architecture for solving the N-Queens problem |
title_sort |
Development of neurofuzzy architecture for solving the N-Queens problem |
author |
Da Silva, Ivan Nunes [UNESP] |
author_facet |
Da Silva, Ivan Nunes [UNESP] Ulson, Jose Alfredo [UNESP] De Souza, Andre Nunes [UNESP] |
author_role |
author |
author2 |
Ulson, Jose Alfredo [UNESP] De Souza, Andre Nunes [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Universidade de São Paulo (USP) |
dc.contributor.author.fl_str_mv |
Da Silva, Ivan Nunes [UNESP] Ulson, Jose Alfredo [UNESP] De Souza, Andre Nunes [UNESP] |
dc.subject.por.fl_str_mv |
Combinatorial optimization Fuzzy inference systems Hopfield network Neural network architecture Recurrent neural network |
topic |
Combinatorial optimization Fuzzy inference systems Hopfield network Neural network architecture Recurrent neural network |
description |
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 recurrent neural networks for solving the N -Queens problem. More specifically, a modified Hopfield network is developed and its internal parameters are explicitly computed using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points, which represent a solution of the considered problem. The network is shown to be completely stable and globally convergent to the solutions of the N -Queens problem. A fuzzy logic controller is also incorporated in the network to minimize convergence time. Simulation results are presented to validate the proposed approach. |
publishDate |
2005 |
dc.date.none.fl_str_mv |
2005-11-01 2022-04-28T20:06:51Z 2022-04-28T20:06:51Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1080/03081070500422695 International Journal of General Systems, v. 34, n. 6, p. 717-734, 2005. 0308-1079 1563-5104 http://hdl.handle.net/11449/224676 10.1080/03081070500422695 2-s2.0-30344469712 |
url |
http://dx.doi.org/10.1080/03081070500422695 http://hdl.handle.net/11449/224676 |
identifier_str_mv |
International Journal of General Systems, v. 34, n. 6, p. 717-734, 2005. 0308-1079 1563-5104 10.1080/03081070500422695 2-s2.0-30344469712 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
International Journal of General Systems |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
717-734 |
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_ |
1799964827463974912 |