Fine-tuning artificial neural networks automatically

Detalhes bibliográficos
Autor(a) principal: Francisco Reinaldo
Data de Publicação: 2007
Outros Autores: Rui Camacho, Luís P. Reis, Demétrio Renó Magalhães
Tipo de documento: Livro
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: https://hdl.handle.net/10216/67390
Resumo: To get the most out of powerful tools expert knowledge is often required. Experts are the ones with the suitable knowledge to tune the tools parameters. In this paper we assess several techniques which can automatically fine tune ANN parameters. Those techniques include the use of GA and Stratified Sampling. The tuning includes the choice of the best ANN structure and the best network biases and their weights. Empirical results achieved in experiments performed using nine heterogeneous data sets show that the use of the proposed Stratified Sampling technique is advantageous.
id RCAP_f3ea5bb3ce6d0733eccee24b165d44b1
oai_identifier_str oai:repositorio-aberto.up.pt:10216/67390
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Fine-tuning artificial neural networks automaticallyEngenharia do conhecimento, Engenharia electrotécnica, electrónica e informáticaKnowledge engineering, Electrical engineering, Electronic engineering, Information engineeringTo get the most out of powerful tools expert knowledge is often required. Experts are the ones with the suitable knowledge to tune the tools parameters. In this paper we assess several techniques which can automatically fine tune ANN parameters. Those techniques include the use of GA and Stratified Sampling. The tuning includes the choice of the best ANN structure and the best network biases and their weights. Empirical results achieved in experiments performed using nine heterogeneous data sets show that the use of the proposed Stratified Sampling technique is advantageous.20072007-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bookapplication/pdfhttps://hdl.handle.net/10216/67390eng10.1007/978-0-387-84814-3_5Francisco ReinaldoRui CamachoLuís P. ReisDemétrio Renó Magalhãesinfo: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:RCAAP2023-11-29T15:25:40Zoai:repositorio-aberto.up.pt:10216/67390Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:23:27.306815Repositório 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 Fine-tuning artificial neural networks automatically
title Fine-tuning artificial neural networks automatically
spellingShingle Fine-tuning artificial neural networks automatically
Francisco Reinaldo
Engenharia do conhecimento, Engenharia electrotécnica, electrónica e informática
Knowledge engineering, Electrical engineering, Electronic engineering, Information engineering
title_short Fine-tuning artificial neural networks automatically
title_full Fine-tuning artificial neural networks automatically
title_fullStr Fine-tuning artificial neural networks automatically
title_full_unstemmed Fine-tuning artificial neural networks automatically
title_sort Fine-tuning artificial neural networks automatically
author Francisco Reinaldo
author_facet Francisco Reinaldo
Rui Camacho
Luís P. Reis
Demétrio Renó Magalhães
author_role author
author2 Rui Camacho
Luís P. Reis
Demétrio Renó Magalhães
author2_role author
author
author
dc.contributor.author.fl_str_mv Francisco Reinaldo
Rui Camacho
Luís P. Reis
Demétrio Renó Magalhães
dc.subject.por.fl_str_mv Engenharia do conhecimento, Engenharia electrotécnica, electrónica e informática
Knowledge engineering, Electrical engineering, Electronic engineering, Information engineering
topic Engenharia do conhecimento, Engenharia electrotécnica, electrónica e informática
Knowledge engineering, Electrical engineering, Electronic engineering, Information engineering
description To get the most out of powerful tools expert knowledge is often required. Experts are the ones with the suitable knowledge to tune the tools parameters. In this paper we assess several techniques which can automatically fine tune ANN parameters. Those techniques include the use of GA and Stratified Sampling. The tuning includes the choice of the best ANN structure and the best network biases and their weights. Empirical results achieved in experiments performed using nine heterogeneous data sets show that the use of the proposed Stratified Sampling technique is advantageous.
publishDate 2007
dc.date.none.fl_str_mv 2007
2007-01-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/book
format book
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/10216/67390
url https://hdl.handle.net/10216/67390
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1007/978-0-387-84814-3_5
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.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_ 1799136150474981376

Registros relacionados