Evolutionary neural network learning algorithms for changing environments

Detalhes bibliográficos
Autor(a) principal: Rocha, Miguel
Data de Publicação: 2004
Outros Autores: Cortez, Paulo, Neves, José
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/1822/426
Resumo: Classical Machine Learning methods are usually developed to work in static data sets. Yet, real world data typically changes over time and there is the need to develop novel adaptive learning algorithms. In this work, a number of algorithms, combining Neural Network learning models and Evolutionary Computation optimization techniques, are compared, being held several simulations based on artificial and real world problems. The results favor the combination of evolution and lifetime learning according to the Baldwin effect framework.
id RCAP_75a30c555faa289caeef3f3536942dc6
oai_identifier_str oai:repositorium.sdum.uminho.pt:1822/426
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Evolutionary neural network learning algorithms for changing environmentsBaldwinian and Lamarckian effectsEvolutionary programmingMultilayer perceptronsClassical Machine Learning methods are usually developed to work in static data sets. Yet, real world data typically changes over time and there is the need to develop novel adaptive learning algorithms. In this work, a number of algorithms, combining Neural Network learning models and Evolutionary Computation optimization techniques, are compared, being held several simulations based on artificial and real world problems. The results favor the combination of evolution and lifetime learning according to the Baldwin effect framework.World Scientific and Engineering Academy and Society (WSEAS)Universidade do MinhoRocha, MiguelCortez, PauloNeves, José2004-042004-04-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/1822/426eng“WSEAS Transactions on Systems”. ISSN 1109-2777. 3:2 (2004) 596-601.1109-2777info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-21T12:53:20Zoai:repositorium.sdum.uminho.pt:1822/426Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:52:41.441732Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Evolutionary neural network learning algorithms for changing environments
title Evolutionary neural network learning algorithms for changing environments
spellingShingle Evolutionary neural network learning algorithms for changing environments
Rocha, Miguel
Baldwinian and Lamarckian effects
Evolutionary programming
Multilayer perceptrons
title_short Evolutionary neural network learning algorithms for changing environments
title_full Evolutionary neural network learning algorithms for changing environments
title_fullStr Evolutionary neural network learning algorithms for changing environments
title_full_unstemmed Evolutionary neural network learning algorithms for changing environments
title_sort Evolutionary neural network learning algorithms for changing environments
author Rocha, Miguel
author_facet Rocha, Miguel
Cortez, Paulo
Neves, José
author_role author
author2 Cortez, Paulo
Neves, José
author2_role author
author
dc.contributor.none.fl_str_mv Universidade do Minho
dc.contributor.author.fl_str_mv Rocha, Miguel
Cortez, Paulo
Neves, José
dc.subject.por.fl_str_mv Baldwinian and Lamarckian effects
Evolutionary programming
Multilayer perceptrons
topic Baldwinian and Lamarckian effects
Evolutionary programming
Multilayer perceptrons
description Classical Machine Learning methods are usually developed to work in static data sets. Yet, real world data typically changes over time and there is the need to develop novel adaptive learning algorithms. In this work, a number of algorithms, combining Neural Network learning models and Evolutionary Computation optimization techniques, are compared, being held several simulations based on artificial and real world problems. The results favor the combination of evolution and lifetime learning according to the Baldwin effect framework.
publishDate 2004
dc.date.none.fl_str_mv 2004-04
2004-04-01T00:00:00Z
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://hdl.handle.net/1822/426
url http://hdl.handle.net/1822/426
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv “WSEAS Transactions on Systems”. ISSN 1109-2777. 3:2 (2004) 596-601.
1109-2777
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv World Scientific and Engineering Academy and Society (WSEAS)
publisher.none.fl_str_mv World Scientific and Engineering Academy and Society (WSEAS)
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799133120308445184

Registros relacionados