Bio-inspired and gradient-based algorithms to train MLPs: The influence of diversity

Página do item simplificado
dc.contributor.authorPasti R.
dc.contributor.authorde Castro L.N.
dc.date.accessioned2024-03-13T01:34:55Z
dc.date.available2024-03-13T01:34:55Z
dc.date.issued2009
dc.description.abstractThis paper has three main goals: (i) to employ two classes of algorithms: bio-inspired and gradient-based to train multi-layer perceptron (MLP) neural networks for pattern classification; (ii) to combine the trained neural networks into ensembles of classifiers; and (iii) to investigate the influence of diversity in the classification performance of individual and ensembles of classifiers. The optimization version of an artificial immune network, named opt-aiNet, particle swarm optimization (PSO) and an evolutionary algorithm (EA) are used as bio-inspired methods to train MLP networks. Besides, the standard backpropagation with momentum (BPM), a quasi-Newton method called DFP and a modified scaled-conjugate gradient (SCGM) are the gradient-based algorithms used to train MLP networks in this work. Comparisons among all the training methods are presented in terms of classification accuracy and diversity of the solutions found. The results obtained suggest that most bio-inspired algorithms deteriorate the diversity of solutions during the search, while immune-based methods, like opt-aiNet, and multiple initializations of standard gradient-based algorithms provide diverse solutions that result in good classification accuracy for the ensembles. © 2008 Elsevier Inc. All rights reserved.
dc.description.firstpage1441
dc.description.issuenumber10
dc.description.lastpage1453
dc.description.volume179
dc.identifier.doi10.1016/j.ins.2008.11.034
dc.identifier.issn0020-0255
dc.identifier.urihttps://dspace.mackenzie.br/handle/10899/37374
dc.relation.ispartofInformation Sciences
dc.rightsAcesso Restrito
dc.subject.otherlanguageArtificial immune systems
dc.subject.otherlanguageBackpropagation
dc.subject.otherlanguageDiversity
dc.subject.otherlanguageEnsembles
dc.subject.otherlanguageEvolutionary algorithm
dc.subject.otherlanguageGradient-based algorithms
dc.subject.otherlanguageMulti-layer perceptrons
dc.subject.otherlanguageParticle swarm optimization
dc.titleBio-inspired and gradient-based algorithms to train MLPs: The influence of diversity
dc.typeArtigo
local.scopus.citations29
local.scopus.eid2-s2.0-61449099344
local.scopus.subjectArtificial immune systems
local.scopus.subjectDiversity
local.scopus.subjectEnsembles
local.scopus.subjectGradient-based algorithms
local.scopus.subjectMulti-layer perceptrons
local.scopus.subjectParticle swarm optimization
local.scopus.updated2024-05-01
local.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=61449099344&origin=inward
Arquivos
Coleções
Artigos de periódico