Neural networks training using the constructivism paradigms

dc.contributorUniversidade Estadual Paulista (Unesp)
dc.date.accessioned2014-05-27T11:18:02Z
dc.date.available2014-05-27T11:18:02Z
dc.date.created2014-05-27T11:18:02Z
dc.date.issued1995-12-01
dc.identifierMidwest Symposium on Circuits and Systems, v. 1, p. 546-549.
dc.identifierhttp://hdl.handle.net/11449/64676
dc.identifier10.1109/MWSCAS.1995.504497
dc.identifierWOS:A1996BF75Z00135
dc.identifier2-s2.0-0029463724
dc.identifier8879964582778840
dc.description.abstractThe 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.
dc.languageeng
dc.relationMidwest Symposium on Circuits and Systems
dc.rightsAcesso aberto
dc.sourceScopus
dc.subjectAdaptive filtering
dc.subjectBackpropagation
dc.subjectComputer simulation
dc.subjectErrors
dc.subjectLearning algorithms
dc.subjectLearning systems
dc.subjectLow pass filters
dc.subjectAlphabetization method
dc.subjectBackpropagation algorithm
dc.subjectConstructivism paradigms
dc.subjectMean square error
dc.subjectMomentum factor
dc.subjectNeural networks training
dc.subjectPiaget philosophy
dc.subjectNeural networks
dc.titleNeural networks training using the constructivism paradigms
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución