ALENA : Adaptive-Length Evolving Neural Arrays

Autores
Corbalán, Leonardo César; Lanzarini, Laura Cristina; De Giusti, Armando Eduardo
Año de publicación
2004
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Evolving neural arrays (ENA) have proved to be capable of learning complex behaviors, i.e., problems whose solution requires strategy learning. For this reason, they present many applications in various areas such as robotics and process control. Unlike conventional methods "based on a single neural network" ENAs are made up of a set of networks organized as an array. Each of them represents a part of the expected solution. This work describes a new method, ALENA, that enhances the solutions obtained by solving the main deficiencies of ENA since it eases the obtaining of specialized components, does not require the explicit decomposition of the problem into subtasks, and is capable of automatically adjusting the arrays length for each particular use. The measurements of the proposed method "applied to problems of obstacle evasion and objects collection" show the superiority of ALENA in relation to the traditional methods that deal with populations of neural networks. SANE has been used in particular as a comparative referent due to its high performance. Eventually, conclusions and some future lines of work are presented.
Facultad de Informática
Materia
Ciencias Informáticas
genetic algorithm
Neural nets
Learning
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc/3.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/9481

id SEDICI_c8676611d277adb6e08004b0fe065305
oai_identifier_str oai:sedici.unlp.edu.ar:10915/9481
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling ALENA : Adaptive-Length Evolving Neural ArraysCorbalán, Leonardo CésarLanzarini, Laura CristinaDe Giusti, Armando EduardoCiencias Informáticasgenetic algorithmNeural netsLearningEvolving neural arrays (ENA) have proved to be capable of learning complex behaviors, i.e., problems whose solution requires strategy learning. For this reason, they present many applications in various areas such as robotics and process control. Unlike conventional methods "based on a single neural network" ENAs are made up of a set of networks organized as an array. Each of them represents a part of the expected solution. This work describes a new method, ALENA, that enhances the solutions obtained by solving the main deficiencies of ENA since it eases the obtaining of specialized components, does not require the explicit decomposition of the problem into subtasks, and is capable of automatically adjusting the arrays length for each particular use. The measurements of the proposed method "applied to problems of obstacle evasion and objects collection" show the superiority of ALENA in relation to the traditional methods that deal with populations of neural networks. SANE has been used in particular as a comparative referent due to its high performance. Eventually, conclusions and some future lines of work are presented.Facultad de Informática2004-04info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionArticulohttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdf59-65http://sedici.unlp.edu.ar/handle/10915/9481enginfo:eu-repo/semantics/altIdentifier/url/http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Apr04-9.pdfinfo:eu-repo/semantics/altIdentifier/issn/1666-6038info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc/3.0/Creative Commons Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T10:50:43Zoai:sedici.unlp.edu.ar:10915/9481Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 10:50:44.158SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv ALENA : Adaptive-Length Evolving Neural Arrays
title ALENA : Adaptive-Length Evolving Neural Arrays
spellingShingle ALENA : Adaptive-Length Evolving Neural Arrays
Corbalán, Leonardo César
Ciencias Informáticas
genetic algorithm
Neural nets
Learning
title_short ALENA : Adaptive-Length Evolving Neural Arrays
title_full ALENA : Adaptive-Length Evolving Neural Arrays
title_fullStr ALENA : Adaptive-Length Evolving Neural Arrays
title_full_unstemmed ALENA : Adaptive-Length Evolving Neural Arrays
title_sort ALENA : Adaptive-Length Evolving Neural Arrays
dc.creator.none.fl_str_mv Corbalán, Leonardo César
Lanzarini, Laura Cristina
De Giusti, Armando Eduardo
author Corbalán, Leonardo César
author_facet Corbalán, Leonardo César
Lanzarini, Laura Cristina
De Giusti, Armando Eduardo
author_role author
author2 Lanzarini, Laura Cristina
De Giusti, Armando Eduardo
author2_role author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
genetic algorithm
Neural nets
Learning
topic Ciencias Informáticas
genetic algorithm
Neural nets
Learning
dc.description.none.fl_txt_mv Evolving neural arrays (ENA) have proved to be capable of learning complex behaviors, i.e., problems whose solution requires strategy learning. For this reason, they present many applications in various areas such as robotics and process control. Unlike conventional methods "based on a single neural network" ENAs are made up of a set of networks organized as an array. Each of them represents a part of the expected solution. This work describes a new method, ALENA, that enhances the solutions obtained by solving the main deficiencies of ENA since it eases the obtaining of specialized components, does not require the explicit decomposition of the problem into subtasks, and is capable of automatically adjusting the arrays length for each particular use. The measurements of the proposed method "applied to problems of obstacle evasion and objects collection" show the superiority of ALENA in relation to the traditional methods that deal with populations of neural networks. SANE has been used in particular as a comparative referent due to its high performance. Eventually, conclusions and some future lines of work are presented.
Facultad de Informática
description Evolving neural arrays (ENA) have proved to be capable of learning complex behaviors, i.e., problems whose solution requires strategy learning. For this reason, they present many applications in various areas such as robotics and process control. Unlike conventional methods "based on a single neural network" ENAs are made up of a set of networks organized as an array. Each of them represents a part of the expected solution. This work describes a new method, ALENA, that enhances the solutions obtained by solving the main deficiencies of ENA since it eases the obtaining of specialized components, does not require the explicit decomposition of the problem into subtasks, and is capable of automatically adjusting the arrays length for each particular use. The measurements of the proposed method "applied to problems of obstacle evasion and objects collection" show the superiority of ALENA in relation to the traditional methods that deal with populations of neural networks. SANE has been used in particular as a comparative referent due to its high performance. Eventually, conclusions and some future lines of work are presented.
publishDate 2004
dc.date.none.fl_str_mv 2004-04
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/10915/9481
url http://sedici.unlp.edu.ar/handle/10915/9481
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Apr04-9.pdf
info:eu-repo/semantics/altIdentifier/issn/1666-6038
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc/3.0/
Creative Commons Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc/3.0/
Creative Commons Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)
dc.format.none.fl_str_mv application/pdf
59-65
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_ 1844615757893206016
score 13.070432