The Generalization Complexity Measure for Continuous Input Data

Autores
Gomez, Ivan; Cannas, Sergio Alejandro; Osenda, Omar; Jerez, Jose M.; Franco, Leonardo
Año de publicación
2014
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
We introduce in this work an extension for the generalization complexity measure to continuous input data. The measure, originallydefined in Boolean space, quantifies the complexity of data in relationship to the prediction accuracy that can be expected whenusing a supervised classifier like a neural network, SVM, and so forth. We first extend the original measure for its use withcontinuous functions to later on, using an approach based on the use of the set of Walsh functions, consider the case of havinga finite number of data points (inputs/outputs pairs), that is, usually the practical case. Using a set of trigonometric functions amodel that gives a relationship between the size of the hidden layerof a neural network and the complexity is constructed. Finally,we demonstrate the application of the introduced complexity measure, by using the generated model, to the problem of estimatingan adequate neural network architecture for real-world data sets.
Fil: Gomez, Ivan. Universidad de Málaga; España
Fil: Cannas, Sergio Alejandro. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Osenda, Omar. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Jerez, Jose M.. Universidad de Málaga; España
Fil: Franco, Leonardo. Universidad de Málaga; España
Materia
Complexity Measure
Neural Networks
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/31822
Acceder
id CONICETDig_5580a830212136a194840aa8fff853e2
oai_identifier_str oai:ri.conicet.gov.ar:11336/31822
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling The Generalization Complexity Measure for Continuous Input DataGomez, IvanCannas, Sergio AlejandroOsenda, OmarJerez, Jose M.Franco, LeonardoComplexity MeasureNeural Networkshttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1We introduce in this work an extension for the generalization complexity measure to continuous input data. The measure, originallydefined in Boolean space, quantifies the complexity of data in relationship to the prediction accuracy that can be expected whenusing a supervised classifier like a neural network, SVM, and so forth. We first extend the original measure for its use withcontinuous functions to later on, using an approach based on the use of the set of Walsh functions, consider the case of havinga finite number of data points (inputs/outputs pairs), that is, usually the practical case. Using a set of trigonometric functions amodel that gives a relationship between the size of the hidden layerof a neural network and the complexity is constructed. Finally,we demonstrate the application of the introduced complexity measure, by using the generated model, to the problem of estimatingan adequate neural network architecture for real-world data sets.Fil: Gomez, Ivan. Universidad de Málaga; EspañaFil: Cannas, Sergio Alejandro. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Osenda, Omar. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; ArgentinaFil: Jerez, Jose M.. Universidad de Málaga; EspañaFil: Franco, Leonardo. Universidad de Málaga; EspañaHindawi Publishing Corporation2014-04info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/31822Franco, Leonardo; Jerez, Jose M.; Osenda, Omar; Cannas, Sergio Alejandro; Gomez, Ivan; The Generalization Complexity Measure for Continuous Input Data; Hindawi Publishing Corporation; The Scientific World Journal; 2014; 4-2014; 1-92356-6140CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1155/2014/815156info:eu-repo/semantics/altIdentifier/url/https://www.hindawi.com/journals/tswj/2014/815156/info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T10:10:36Zoai:ri.conicet.gov.ar:11336/31822instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 10:10:37.071CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv The Generalization Complexity Measure for Continuous Input Data
title The Generalization Complexity Measure for Continuous Input Data
spellingShingle The Generalization Complexity Measure for Continuous Input Data
Gomez, Ivan
Complexity Measure
Neural Networks
title_short The Generalization Complexity Measure for Continuous Input Data
title_full The Generalization Complexity Measure for Continuous Input Data
title_fullStr The Generalization Complexity Measure for Continuous Input Data
title_full_unstemmed The Generalization Complexity Measure for Continuous Input Data
title_sort The Generalization Complexity Measure for Continuous Input Data
dc.creator.none.fl_str_mv Gomez, Ivan
Cannas, Sergio Alejandro
Osenda, Omar
Jerez, Jose M.
Franco, Leonardo
author Gomez, Ivan
author_facet Gomez, Ivan
Cannas, Sergio Alejandro
Osenda, Omar
Jerez, Jose M.
Franco, Leonardo
author_role author
author2 Cannas, Sergio Alejandro
Osenda, Omar
Jerez, Jose M.
Franco, Leonardo
author2_role author
author
author
author
dc.subject.none.fl_str_mv Complexity Measure
Neural Networks
topic Complexity Measure
Neural Networks
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv We introduce in this work an extension for the generalization complexity measure to continuous input data. The measure, originallydefined in Boolean space, quantifies the complexity of data in relationship to the prediction accuracy that can be expected whenusing a supervised classifier like a neural network, SVM, and so forth. We first extend the original measure for its use withcontinuous functions to later on, using an approach based on the use of the set of Walsh functions, consider the case of havinga finite number of data points (inputs/outputs pairs), that is, usually the practical case. Using a set of trigonometric functions amodel that gives a relationship between the size of the hidden layerof a neural network and the complexity is constructed. Finally,we demonstrate the application of the introduced complexity measure, by using the generated model, to the problem of estimatingan adequate neural network architecture for real-world data sets.
Fil: Gomez, Ivan. Universidad de Málaga; España
Fil: Cannas, Sergio Alejandro. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Osenda, Omar. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Jerez, Jose M.. Universidad de Málaga; España
Fil: Franco, Leonardo. Universidad de Málaga; España
description We introduce in this work an extension for the generalization complexity measure to continuous input data. The measure, originallydefined in Boolean space, quantifies the complexity of data in relationship to the prediction accuracy that can be expected whenusing a supervised classifier like a neural network, SVM, and so forth. We first extend the original measure for its use withcontinuous functions to later on, using an approach based on the use of the set of Walsh functions, consider the case of havinga finite number of data points (inputs/outputs pairs), that is, usually the practical case. Using a set of trigonometric functions amodel that gives a relationship between the size of the hidden layerof a neural network and the complexity is constructed. Finally,we demonstrate the application of the introduced complexity measure, by using the generated model, to the problem of estimatingan adequate neural network architecture for real-world data sets.
publishDate 2014
dc.date.none.fl_str_mv 2014-04
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
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://hdl.handle.net/11336/31822
Franco, Leonardo; Jerez, Jose M.; Osenda, Omar; Cannas, Sergio Alejandro; Gomez, Ivan; The Generalization Complexity Measure for Continuous Input Data; Hindawi Publishing Corporation; The Scientific World Journal; 2014; 4-2014; 1-9
2356-6140
CONICET Digital
CONICET
url http://hdl.handle.net/11336/31822
identifier_str_mv Franco, Leonardo; Jerez, Jose M.; Osenda, Omar; Cannas, Sergio Alejandro; Gomez, Ivan; The Generalization Complexity Measure for Continuous Input Data; Hindawi Publishing Corporation; The Scientific World Journal; 2014; 4-2014; 1-9
2356-6140
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1155/2014/815156
info:eu-repo/semantics/altIdentifier/url/https://www.hindawi.com/journals/tswj/2014/815156/
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Hindawi Publishing Corporation
publisher.none.fl_str_mv Hindawi Publishing Corporation
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842270127087681536
score 13.13397

Publicaciones similares