Studying bloat control and maintenance of effective code in linear genetic programming for symbolic regression

Página do item simplificado
dc.citation.volume180
dc.contributor.authordal Piccol Sotto, Leo Francoso [UNIFESP]
dc.contributor.authorde Melo, Vinicius Veloso [UNIFESP]
dc.coverageAmsterdam
dc.date.accessioned2020-08-21T16:59:54Z
dc.date.available2020-08-21T16:59:54Z
dc.date.issued2016
dc.description.abstractLinear Genetic Programming (LGP) is an Evolutionary Computation algorithm, inspired in the Genetic Programming (GP) algorithm. Instead of using the standard tree representation of GP, LGP evolves a linear program, which causes a graph-based data flow with code reuse. LGP has been shown to outperform GP in several problems, including Symbolic Regression (SReg), and to produce simpler solutions. In this paper, we propose several LGP variants and compare them with a traditional LGP algorithm on a set of benchmark SReg functions from the literature. The main objectives of the variants were to both control bloat and privilege useful code in the population. Here we evaluate their effects during the evolution process and in the quality of the final solutions. Analysis of the results showed that bloat control and effective code maintenance worked, but they did not guarantee improvement in solution quality. (C) 2015 Elsevier B.V. All rights reserved.en
dc.description.affiliationFed Univ Sao Paulo UNIFESP, Inst Sci & Technol ICT, Sao Jose Dos Campos, SP, Brazil
dc.description.affiliationUnifespFed Univ Sao Paulo UNIFESP, Inst Sci & Technol ICT, Sao Jose Dos Campos, SP, Brazil
dc.description.sourceWeb of Science
dc.description.sponsorshipFundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP)
dc.description.sponsorshipComissao Nacional de Desenvolvimento Cientifico e Tecnologico (CNPq Universal)
dc.description.sponsorshipCoordenadoria de Apoio a Pesquisa e Ensino Superior (CAPES Science without Borders)
dc.description.sponsorshipIDFAPESP: 2013/20606-0
dc.description.sponsorshipIDCNPq Universal: 486950/2013-1
dc.description.sponsorshipIDCAPES: 12180-13-0
dc.format.extent79-93
dc.identifierhttp://dx.doi.org/10.1016/j.neucom.2015.10.109
dc.identifier.citationNeurocomputing. Amsterdam, v. 180, p. 79-93, 2016.
dc.identifier.doi10.1016/j.neucom.2015.10.109
dc.identifier.issn0925-2312
dc.identifier.urihttps://repositorio.unifesp.br/handle/11600/57799
dc.identifier.wosWOS:000370107900008
dc.language.isoeng
dc.publisherElsevier Science Bv
dc.relation.ispartofNeurocomputing
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subjectBloat controlen
dc.subjectEffective codeen
dc.subjectSymbolic regressionen
dc.subjectLinear genetic programmingen
dc.titleStudying bloat control and maintenance of effective code in linear genetic programming for symbolic regressionen
dc.typeinfo:eu-repo/semantics/article
Arquivos
Coleções
ICT - Artigos