Improving network generalization through selection of examples

Autores
Cannas, Sergio A.; Franco, Leonardo
Año de publicación
1998
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
In this work, we study how the selection of examples affects the learning procedure in a neural network and its relationship with the complexity of the function under study and its architecture. We focus on three different problems: parity, addition of two number and bitshifting implemented on feed-forward Neural Networks. For the parity problem, one of the most used problems for testing learning algorithms, we obtain the result that only the use of the whole set of examples assures global learnings. For the other two functions we show that generalization can be considerably improved with a particular selection of examples instead of a random one.
Sistemas Inteligentes
Red de Universidades con Carreras en Informática (RedUNCI)
Materia
Ciencias Informáticas
Informática
Neural nets
Network Architecture and Design
neural networks
machine learning
generalization
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/24820
Acceder
id SEDICI_30779056c0d6cf79e1f276f135029fd3
oai_identifier_str oai:sedici.unlp.edu.ar:10915/24820
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Improving network generalization through selection of examplesCannas, Sergio A.Franco, LeonardoCiencias InformáticasInformáticaNeural netsNetwork Architecture and Designneural networksmachine learninggeneralizationIn this work, we study how the selection of examples affects the learning procedure in a neural network and its relationship with the complexity of the function under study and its architecture. We focus on three different problems: parity, addition of two number and bitshifting implemented on feed-forward Neural Networks. For the parity problem, one of the most used problems for testing learning algorithms, we obtain the result that only the use of the whole set of examples assures global learnings. For the other two functions we show that generalization can be considerably improved with a particular selection of examples instead of a random one.Sistemas InteligentesRed de Universidades con Carreras en Informática (RedUNCI)1998-10info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdfhttp://sedici.unlp.edu.ar/handle/10915/24820enginfo:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/2.5/ar/Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-17T09:39:26Zoai:sedici.unlp.edu.ar:10915/24820Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-17 09:39:26.8SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Improving network generalization through selection of examples
title Improving network generalization through selection of examples
spellingShingle Improving network generalization through selection of examples
Cannas, Sergio A.
Ciencias Informáticas
Informática
Neural nets
Network Architecture and Design
neural networks
machine learning
generalization
title_short Improving network generalization through selection of examples
title_full Improving network generalization through selection of examples
title_fullStr Improving network generalization through selection of examples
title_full_unstemmed Improving network generalization through selection of examples
title_sort Improving network generalization through selection of examples
dc.creator.none.fl_str_mv Cannas, Sergio A.
Franco, Leonardo
author Cannas, Sergio A.
author_facet Cannas, Sergio A.
Franco, Leonardo
author_role author
author2 Franco, Leonardo
author2_role author
dc.subject.none.fl_str_mv Ciencias Informáticas
Informática
Neural nets
Network Architecture and Design
neural networks
machine learning
generalization
topic Ciencias Informáticas
Informática
Neural nets
Network Architecture and Design
neural networks
machine learning
generalization
dc.description.none.fl_txt_mv In this work, we study how the selection of examples affects the learning procedure in a neural network and its relationship with the complexity of the function under study and its architecture. We focus on three different problems: parity, addition of two number and bitshifting implemented on feed-forward Neural Networks. For the parity problem, one of the most used problems for testing learning algorithms, we obtain the result that only the use of the whole set of examples assures global learnings. For the other two functions we show that generalization can be considerably improved with a particular selection of examples instead of a random one.
Sistemas Inteligentes
Red de Universidades con Carreras en Informática (RedUNCI)
description In this work, we study how the selection of examples affects the learning procedure in a neural network and its relationship with the complexity of the function under study and its architecture. We focus on three different problems: parity, addition of two number and bitshifting implemented on feed-forward Neural Networks. For the parity problem, one of the most used problems for testing learning algorithms, we obtain the result that only the use of the whole set of examples assures global learnings. For the other two functions we show that generalization can be considerably improved with a particular selection of examples instead of a random one.
publishDate 1998
dc.date.none.fl_str_mv 1998-10
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/24820
url http://sedici.unlp.edu.ar/handle/10915/24820
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)
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_ 1843532067687628800
score 13.001348

Publicaciones similares