Eigenvalue decay: a new method for neural network regularization
Autor(a) principal: | |
---|---|
Data de Publicação: | 2014 |
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/10316/27727 https://doi.org/10.1016/j.neucom.2013.08.005 |
Resumo: | This paper proposes two new training algorithms for multilayer perceptrons based on evolutionary computation, regularization, and transduction. Regularization is a commonly used technique for preventing the learning algorithm from overfitting the training data. In this context, this work introduces and analyzes a novel regularization scheme for neural networks (NNs) named eigenvalue decay, which aims at improving the classification margin. The introduction of eigenvalue decay led to the development of a new training method based on the same principles of SVM, and so named Support Vector NN (SVNN). Finally, by analogy with the transductive SVM (TSVM), it is proposed a transductive NN (TNN), by exploiting SVNN in order to address transductive learning. The effectiveness of the proposed algorithms is evaluated on seven benchmark datasets. |
id |
RCAP_54bae9b85b6c8903116aab01e0dda9b8 |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/27727 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Eigenvalue decay: a new method for neural network regularizationTransductionRegularizationGenetic algorithmClassification marginNeural networkThis paper proposes two new training algorithms for multilayer perceptrons based on evolutionary computation, regularization, and transduction. Regularization is a commonly used technique for preventing the learning algorithm from overfitting the training data. In this context, this work introduces and analyzes a novel regularization scheme for neural networks (NNs) named eigenvalue decay, which aims at improving the classification margin. The introduction of eigenvalue decay led to the development of a new training method based on the same principles of SVM, and so named Support Vector NN (SVNN). Finally, by analogy with the transductive SVM (TSVM), it is proposed a transductive NN (TNN), by exploiting SVNN in order to address transductive learning. The effectiveness of the proposed algorithms is evaluated on seven benchmark datasets.Elsevier2014-01-26info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/27727http://hdl.handle.net/10316/27727https://doi.org/10.1016/j.neucom.2013.08.005engLUDWIG, Oswaldo; NUNES, Urbano; ARAUJO, Rui - Eigenvalue decay: a new method for neural network regularization. "Neurocomputing". ISSN 0925-2312. Vol. 124 (2014) p. 33–420925-2312http://www.sciencedirect.com/science/article/pii/S0925231213008333Ludwig, OswaldoNunes, UrbanoAraujo, 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:RCAAP2020-05-25T12:19:56Zoai:estudogeral.uc.pt:10316/27727Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:53:46.402737Repositório 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 |
Eigenvalue decay: a new method for neural network regularization |
title |
Eigenvalue decay: a new method for neural network regularization |
spellingShingle |
Eigenvalue decay: a new method for neural network regularization Ludwig, Oswaldo Transduction Regularization Genetic algorithm Classification margin Neural network |
title_short |
Eigenvalue decay: a new method for neural network regularization |
title_full |
Eigenvalue decay: a new method for neural network regularization |
title_fullStr |
Eigenvalue decay: a new method for neural network regularization |
title_full_unstemmed |
Eigenvalue decay: a new method for neural network regularization |
title_sort |
Eigenvalue decay: a new method for neural network regularization |
author |
Ludwig, Oswaldo |
author_facet |
Ludwig, Oswaldo Nunes, Urbano Araujo, Rui |
author_role |
author |
author2 |
Nunes, Urbano Araujo, Rui |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Ludwig, Oswaldo Nunes, Urbano Araujo, Rui |
dc.subject.por.fl_str_mv |
Transduction Regularization Genetic algorithm Classification margin Neural network |
topic |
Transduction Regularization Genetic algorithm Classification margin Neural network |
description |
This paper proposes two new training algorithms for multilayer perceptrons based on evolutionary computation, regularization, and transduction. Regularization is a commonly used technique for preventing the learning algorithm from overfitting the training data. In this context, this work introduces and analyzes a novel regularization scheme for neural networks (NNs) named eigenvalue decay, which aims at improving the classification margin. The introduction of eigenvalue decay led to the development of a new training method based on the same principles of SVM, and so named Support Vector NN (SVNN). Finally, by analogy with the transductive SVM (TSVM), it is proposed a transductive NN (TNN), by exploiting SVNN in order to address transductive learning. The effectiveness of the proposed algorithms is evaluated on seven benchmark datasets. |
publishDate |
2014 |
dc.date.none.fl_str_mv |
2014-01-26 |
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/10316/27727 http://hdl.handle.net/10316/27727 https://doi.org/10.1016/j.neucom.2013.08.005 |
url |
http://hdl.handle.net/10316/27727 https://doi.org/10.1016/j.neucom.2013.08.005 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
LUDWIG, Oswaldo; NUNES, Urbano; ARAUJO, Rui - Eigenvalue decay: a new method for neural network regularization. "Neurocomputing". ISSN 0925-2312. Vol. 124 (2014) p. 33–42 0925-2312 http://www.sciencedirect.com/science/article/pii/S0925231213008333 |
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_ |
1799133823795986432 |