Neural networks training using the constructivism paradigms
Autor(a) principal: | |
---|---|
Data de Publicação: | 1995 |
Outros Autores: | |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/MWSCAS.1995.504497 http://hdl.handle.net/11449/64676 |
Resumo: | The Backpropagation Algorithm (BA) is the standard method for training multilayer Artificial Neural Networks (ANN), although it converges very slowly and can stop in a local minimum. We present a new method for neural network training using the BA inspired on constructivism, an alphabetization method proposed by Emilia Ferreiro based on Piaget philosophy. Simulation results show that the proposed configuration usually obtains a lower final mean square error, when compared with the standard BA and with the BA with momentum factor. |
id |
UNSP_cf71fc9cadc571d51d973483473eb13a |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/64676 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Neural networks training using the constructivism paradigmsAdaptive filteringBackpropagationComputer simulationErrorsLearning algorithmsLearning systemsLow pass filtersAlphabetization methodBackpropagation algorithmConstructivism paradigmsMean square errorMomentum factorNeural networks trainingPiaget philosophyNeural networksThe Backpropagation Algorithm (BA) is the standard method for training multilayer Artificial Neural Networks (ANN), although it converges very slowly and can stop in a local minimum. We present a new method for neural network training using the BA inspired on constructivism, an alphabetization method proposed by Emilia Ferreiro based on Piaget philosophy. Simulation results show that the proposed configuration usually obtains a lower final mean square error, when compared with the standard BA and with the BA with momentum factor.FEIS - UNESP, Ilha SolteiraFEIS - UNESP, Ilha SolteiraUniversidade Estadual Paulista (Unesp)Teixeira, Marcelo Carvalho Minhoto [UNESP]Lamas, Decio [UNESP]2014-05-27T11:18:02Z2014-05-27T11:18:02Z1995-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject546-549http://dx.doi.org/10.1109/MWSCAS.1995.504497Midwest Symposium on Circuits and Systems, v. 1, p. 546-549.http://hdl.handle.net/11449/6467610.1109/MWSCAS.1995.504497WOS:A1996BF75Z001352-s2.0-00294637248879964582778840Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengMidwest Symposium on Circuits and Systemsinfo:eu-repo/semantics/openAccess2021-10-23T21:41:33Zoai:repositorio.unesp.br:11449/64676Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T21:41:33Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Neural networks training using the constructivism paradigms |
title |
Neural networks training using the constructivism paradigms |
spellingShingle |
Neural networks training using the constructivism paradigms Teixeira, Marcelo Carvalho Minhoto [UNESP] Adaptive filtering Backpropagation Computer simulation Errors Learning algorithms Learning systems Low pass filters Alphabetization method Backpropagation algorithm Constructivism paradigms Mean square error Momentum factor Neural networks training Piaget philosophy Neural networks |
title_short |
Neural networks training using the constructivism paradigms |
title_full |
Neural networks training using the constructivism paradigms |
title_fullStr |
Neural networks training using the constructivism paradigms |
title_full_unstemmed |
Neural networks training using the constructivism paradigms |
title_sort |
Neural networks training using the constructivism paradigms |
author |
Teixeira, Marcelo Carvalho Minhoto [UNESP] |
author_facet |
Teixeira, Marcelo Carvalho Minhoto [UNESP] Lamas, Decio [UNESP] |
author_role |
author |
author2 |
Lamas, Decio [UNESP] |
author2_role |
author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Teixeira, Marcelo Carvalho Minhoto [UNESP] Lamas, Decio [UNESP] |
dc.subject.por.fl_str_mv |
Adaptive filtering Backpropagation Computer simulation Errors Learning algorithms Learning systems Low pass filters Alphabetization method Backpropagation algorithm Constructivism paradigms Mean square error Momentum factor Neural networks training Piaget philosophy Neural networks |
topic |
Adaptive filtering Backpropagation Computer simulation Errors Learning algorithms Learning systems Low pass filters Alphabetization method Backpropagation algorithm Constructivism paradigms Mean square error Momentum factor Neural networks training Piaget philosophy Neural networks |
description |
The Backpropagation Algorithm (BA) is the standard method for training multilayer Artificial Neural Networks (ANN), although it converges very slowly and can stop in a local minimum. We present a new method for neural network training using the BA inspired on constructivism, an alphabetization method proposed by Emilia Ferreiro based on Piaget philosophy. Simulation results show that the proposed configuration usually obtains a lower final mean square error, when compared with the standard BA and with the BA with momentum factor. |
publishDate |
1995 |
dc.date.none.fl_str_mv |
1995-12-01 2014-05-27T11:18:02Z 2014-05-27T11:18:02Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/MWSCAS.1995.504497 Midwest Symposium on Circuits and Systems, v. 1, p. 546-549. http://hdl.handle.net/11449/64676 10.1109/MWSCAS.1995.504497 WOS:A1996BF75Z00135 2-s2.0-0029463724 8879964582778840 |
url |
http://dx.doi.org/10.1109/MWSCAS.1995.504497 http://hdl.handle.net/11449/64676 |
identifier_str_mv |
Midwest Symposium on Circuits and Systems, v. 1, p. 546-549. 10.1109/MWSCAS.1995.504497 WOS:A1996BF75Z00135 2-s2.0-0029463724 8879964582778840 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Midwest Symposium on Circuits and Systems |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
546-549 |
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_ |
1799965199812263936 |