Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development
Autor(a) principal: | |
---|---|
Data de Publicação: | 2013 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10316/27282 https://doi.org/10.1016/j.neucom.2013.05.024 |
Resumo: | In the last decades ensemble learning has established itself as a valuable strategy within the computational intelligence modeling and machine learning community. Ensemble learning is a paradigm where multiple models combine in some way their decisions, or their learning algorithms, or different data to improve the prediction performance. Ensemble learning aims at improving the generalization ability and the reliability of the system. Key factors of ensemble systems are diversity, training and combining ensemble members to improve the ensemble system performance. Since there is no unified procedure to address all these issues, this work proposes and compares Genetic Algorithm and Simulated Annealing based approaches for the automatic development of Neural Network Ensembles for regression problems. The main contribution of this work is the development of optimization techniques that selects the best subset of models to be aggregated taking into account all the key factors of ensemble systems (e.g., diversity, training ensemble members and combination strategy). Experiments on two well-known data sets are reported to evaluate the effectiveness of the proposed methodologies. Results show that these outperform other approaches including Simple Bagging, Negative Correlation Learning (NCL), AdaBoost and GASEN in terms of generalization ability. |
id |
RCAP_8a9d1efe7f2c017be78e1ea72898a64d |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/27282 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble developmentEnsemble learningNeural networkGenetic algorithmSimulated annealingIn the last decades ensemble learning has established itself as a valuable strategy within the computational intelligence modeling and machine learning community. Ensemble learning is a paradigm where multiple models combine in some way their decisions, or their learning algorithms, or different data to improve the prediction performance. Ensemble learning aims at improving the generalization ability and the reliability of the system. Key factors of ensemble systems are diversity, training and combining ensemble members to improve the ensemble system performance. Since there is no unified procedure to address all these issues, this work proposes and compares Genetic Algorithm and Simulated Annealing based approaches for the automatic development of Neural Network Ensembles for regression problems. The main contribution of this work is the development of optimization techniques that selects the best subset of models to be aggregated taking into account all the key factors of ensemble systems (e.g., diversity, training ensemble members and combination strategy). Experiments on two well-known data sets are reported to evaluate the effectiveness of the proposed methodologies. Results show that these outperform other approaches including Simple Bagging, Negative Correlation Learning (NCL), AdaBoost and GASEN in terms of generalization ability.Elsevier2013-12-09info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/27282http://hdl.handle.net/10316/27282https://doi.org/10.1016/j.neucom.2013.05.024engSOARES, Symone; ANTUNES, Carlos Henggeler; ARAÚJO, Rui - Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development. "Neurocomputing". ISSN 0925-2312. Vol. 121 (2013) p. 498-5110925-2312http://www.sciencedirect.com/science/article/pii/S0925231213005791Soares, SymoneAntunes, Carlos HenggelerAraújo, Ruiinfo: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:RCAAP2020-05-25T12:06:47Zoai:estudogeral.uc.pt:10316/27282Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:57:55.497015Repositório 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 |
Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development |
title |
Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development |
spellingShingle |
Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development Soares, Symone Ensemble learning Neural network Genetic algorithm Simulated annealing |
title_short |
Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development |
title_full |
Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development |
title_fullStr |
Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development |
title_full_unstemmed |
Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development |
title_sort |
Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development |
author |
Soares, Symone |
author_facet |
Soares, Symone Antunes, Carlos Henggeler Araújo, Rui |
author_role |
author |
author2 |
Antunes, Carlos Henggeler Araújo, Rui |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Soares, Symone Antunes, Carlos Henggeler Araújo, Rui |
dc.subject.por.fl_str_mv |
Ensemble learning Neural network Genetic algorithm Simulated annealing |
topic |
Ensemble learning Neural network Genetic algorithm Simulated annealing |
description |
In the last decades ensemble learning has established itself as a valuable strategy within the computational intelligence modeling and machine learning community. Ensemble learning is a paradigm where multiple models combine in some way their decisions, or their learning algorithms, or different data to improve the prediction performance. Ensemble learning aims at improving the generalization ability and the reliability of the system. Key factors of ensemble systems are diversity, training and combining ensemble members to improve the ensemble system performance. Since there is no unified procedure to address all these issues, this work proposes and compares Genetic Algorithm and Simulated Annealing based approaches for the automatic development of Neural Network Ensembles for regression problems. The main contribution of this work is the development of optimization techniques that selects the best subset of models to be aggregated taking into account all the key factors of ensemble systems (e.g., diversity, training ensemble members and combination strategy). Experiments on two well-known data sets are reported to evaluate the effectiveness of the proposed methodologies. Results show that these outperform other approaches including Simple Bagging, Negative Correlation Learning (NCL), AdaBoost and GASEN in terms of generalization ability. |
publishDate |
2013 |
dc.date.none.fl_str_mv |
2013-12-09 |
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/10316/27282 http://hdl.handle.net/10316/27282 https://doi.org/10.1016/j.neucom.2013.05.024 |
url |
http://hdl.handle.net/10316/27282 https://doi.org/10.1016/j.neucom.2013.05.024 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
SOARES, Symone; ANTUNES, Carlos Henggeler; ARAÚJO, Rui - Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development. "Neurocomputing". ISSN 0925-2312. Vol. 121 (2013) p. 498-511 0925-2312 http://www.sciencedirect.com/science/article/pii/S0925231213005791 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
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_ |
1799133869336690688 |