Evolving neural arrays: a new mechanism for learning complex action sequences

Autores
Corbalán, Leonardo César; Lanzarini, Laura Cristina
Año de publicación
2017
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Incremental evolution has proved to be an extremely useful mechanism in complex actions sequence learning. Its performance is based on the decomposition of the original problem into increasingly complex stages whose learning is carried out sequentially, starting from the simplest stage and thus increasing its generality and difficulty. The present work proposes neural array applications as a novel mechanism for complex actions sequence learning. Each array is composed by several neural nets obtained by means of an evolving process allowing them to acquire various degrees of specialization. Neural nets constituting the same array are organized so that, in each assessment, there is only one in charge of its response. The proposed strategy is applied to problems presented by obstacle evasion and target reaching as a means to show the capability of this proposal to solve complex problems. The measurements carried out show the superiority of evolving neural arrays over traditional neuroevolving methods that handle neural network populations – SANE is being particularly used as a comparative reference due to its high performance. Neural array capability to recover from previous defective evolving stages has been tested, evincing highly plausible final successful outcomes – even in those adverse cases. Finally, conclusions are presented as well as some future lines of work.
Instituto de Investigación en Informática
Materia
Ciencias Informáticas
Evolving neural nets
Learning
Complex actions sequence learning
Incremental evolution
Genetic algorithms
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/103776

id SEDICI_cfdf95e0472452cdc5f4b1502df69cd0
oai_identifier_str oai:sedici.unlp.edu.ar:10915/103776
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Evolving neural arrays: a new mechanism for learning complex action sequencesCorbalán, Leonardo CésarLanzarini, Laura CristinaCiencias InformáticasEvolving neural netsLearningComplex actions sequence learningIncremental evolutionGenetic algorithmsIncremental evolution has proved to be an extremely useful mechanism in complex actions sequence learning. Its performance is based on the decomposition of the original problem into increasingly complex stages whose learning is carried out sequentially, starting from the simplest stage and thus increasing its generality and difficulty. The present work proposes neural array applications as a novel mechanism for complex actions sequence learning. Each array is composed by several neural nets obtained by means of an evolving process allowing them to acquire various degrees of specialization. Neural nets constituting the same array are organized so that, in each assessment, there is only one in charge of its response. The proposed strategy is applied to problems presented by obstacle evasion and target reaching as a means to show the capability of this proposal to solve complex problems. The measurements carried out show the superiority of evolving neural arrays over traditional neuroevolving methods that handle neural network populations – SANE is being particularly used as a comparative reference due to its high performance. Neural array capability to recover from previous defective evolving stages has been tested, evincing highly plausible final successful outcomes – even in those adverse cases. Finally, conclusions are presented as well as some future lines of work.Instituto de Investigación en Informática2017info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionArticulohttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfhttp://sedici.unlp.edu.ar/handle/10915/103776enginfo:eu-repo/semantics/altIdentifier/url/http://www.clei.org/cleiej/index.php/cleiej/article/view/348info:eu-repo/semantics/altIdentifier/issn/0717-5000info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T11:22:33Zoai:sedici.unlp.edu.ar:10915/103776Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 11:22:34.229SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Evolving neural arrays: a new mechanism for learning complex action sequences
title Evolving neural arrays: a new mechanism for learning complex action sequences
spellingShingle Evolving neural arrays: a new mechanism for learning complex action sequences
Corbalán, Leonardo César
Ciencias Informáticas
Evolving neural nets
Learning
Complex actions sequence learning
Incremental evolution
Genetic algorithms
title_short Evolving neural arrays: a new mechanism for learning complex action sequences
title_full Evolving neural arrays: a new mechanism for learning complex action sequences
title_fullStr Evolving neural arrays: a new mechanism for learning complex action sequences
title_full_unstemmed Evolving neural arrays: a new mechanism for learning complex action sequences
title_sort Evolving neural arrays: a new mechanism for learning complex action sequences
dc.creator.none.fl_str_mv Corbalán, Leonardo César
Lanzarini, Laura Cristina
author Corbalán, Leonardo César
author_facet Corbalán, Leonardo César
Lanzarini, Laura Cristina
author_role author
author2 Lanzarini, Laura Cristina
author2_role author
dc.subject.none.fl_str_mv Ciencias Informáticas
Evolving neural nets
Learning
Complex actions sequence learning
Incremental evolution
Genetic algorithms
topic Ciencias Informáticas
Evolving neural nets
Learning
Complex actions sequence learning
Incremental evolution
Genetic algorithms
dc.description.none.fl_txt_mv Incremental evolution has proved to be an extremely useful mechanism in complex actions sequence learning. Its performance is based on the decomposition of the original problem into increasingly complex stages whose learning is carried out sequentially, starting from the simplest stage and thus increasing its generality and difficulty. The present work proposes neural array applications as a novel mechanism for complex actions sequence learning. Each array is composed by several neural nets obtained by means of an evolving process allowing them to acquire various degrees of specialization. Neural nets constituting the same array are organized so that, in each assessment, there is only one in charge of its response. The proposed strategy is applied to problems presented by obstacle evasion and target reaching as a means to show the capability of this proposal to solve complex problems. The measurements carried out show the superiority of evolving neural arrays over traditional neuroevolving methods that handle neural network populations – SANE is being particularly used as a comparative reference due to its high performance. Neural array capability to recover from previous defective evolving stages has been tested, evincing highly plausible final successful outcomes – even in those adverse cases. Finally, conclusions are presented as well as some future lines of work.
Instituto de Investigación en Informática
description Incremental evolution has proved to be an extremely useful mechanism in complex actions sequence learning. Its performance is based on the decomposition of the original problem into increasingly complex stages whose learning is carried out sequentially, starting from the simplest stage and thus increasing its generality and difficulty. The present work proposes neural array applications as a novel mechanism for complex actions sequence learning. Each array is composed by several neural nets obtained by means of an evolving process allowing them to acquire various degrees of specialization. Neural nets constituting the same array are organized so that, in each assessment, there is only one in charge of its response. The proposed strategy is applied to problems presented by obstacle evasion and target reaching as a means to show the capability of this proposal to solve complex problems. The measurements carried out show the superiority of evolving neural arrays over traditional neuroevolving methods that handle neural network populations – SANE is being particularly used as a comparative reference due to its high performance. Neural array capability to recover from previous defective evolving stages has been tested, evincing highly plausible final successful outcomes – even in those adverse cases. Finally, conclusions are presented as well as some future lines of work.
publishDate 2017
dc.date.none.fl_str_mv 2017
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Articulo
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/103776
url http://sedici.unlp.edu.ar/handle/10915/103776
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://www.clei.org/cleiej/index.php/cleiej/article/view/348
info:eu-repo/semantics/altIdentifier/issn/0717-5000
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1844616101761122304
score 13.070432