Approximate linear dependence as a design method for Kernel prototype-based classifiers

Detalhes bibliográficos
Autor(a) principal: Coelho, David Nascimento
Data de Publicação: 2019
Outros Autores: Barreto, Guilherme de Alencar
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da Universidade Federal do Ceará (UFC)
Texto Completo: http://www.repositorio.ufc.br/handle/riufc/70707
Resumo: The approximate linear dependence (ALD) method is a sparsification procedure used to build a dictionary of samples extracted from a data set. The extracted samples are approximately linearly independent in a high-dimensional kernel reproducing Hilbert space. In this paper, we argue that the ALD method itself can be used to select relevant prototypes from a training data set and use them to classify new samples using kernelized distances. The results obtained from intensive experimentation with several datasets indicate that the proposed approach is viable to be used as a standalone classifier.
id UFC-7_4483a6e9afac971e6e08970e12fc584e
oai_identifier_str oai:repositorio.ufc.br:riufc/70707
network_acronym_str UFC-7
network_name_str Repositório Institucional da Universidade Federal do Ceará (UFC)
repository_id_str
spelling Approximate linear dependence as a design method for Kernel prototype-based classifiersPrototype-based classifiersSparsificationApproximate linear dependenceKernel classifiersKernel SOMThe approximate linear dependence (ALD) method is a sparsification procedure used to build a dictionary of samples extracted from a data set. The extracted samples are approximately linearly independent in a high-dimensional kernel reproducing Hilbert space. In this paper, we argue that the ALD method itself can be used to select relevant prototypes from a training data set and use them to classify new samples using kernelized distances. The results obtained from intensive experimentation with several datasets indicate that the proposed approach is viable to be used as a standalone classifier.International Workshop on Self-Organizing Maps2023-02-09T16:49:52Z2023-02-09T16:49:52Z2019info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectapplication/pdfCOELHO, D. N.; BARRETO, G. A. Approximate linear dependence as a design method for Kernel prototype-based classifiers. In: INTERNATIONAL WORKSHOP ON SELF-ORGANIZING MAPS, 13., 2019, Barcelona. Anais... Barcelona, 2013. p. 241-250.http://www.repositorio.ufc.br/handle/riufc/70707Coelho, David NascimentoBarreto, Guilherme de Alencarengreponame:Repositório Institucional da Universidade Federal do Ceará (UFC)instname:Universidade Federal do Ceará (UFC)instacron:UFCinfo:eu-repo/semantics/openAccess2023-02-09T16:49:52Zoai:repositorio.ufc.br:riufc/70707Repositório InstitucionalPUBhttp://www.repositorio.ufc.br/ri-oai/requestbu@ufc.br || repositorio@ufc.bropendoar:2024-09-11T18:49:50.554642Repositório Institucional da Universidade Federal do Ceará (UFC) - Universidade Federal do Ceará (UFC)false
dc.title.none.fl_str_mv Approximate linear dependence as a design method for Kernel prototype-based classifiers
title Approximate linear dependence as a design method for Kernel prototype-based classifiers
spellingShingle Approximate linear dependence as a design method for Kernel prototype-based classifiers
Coelho, David Nascimento
Prototype-based classifiers
Sparsification
Approximate linear dependence
Kernel classifiers
Kernel SOM
title_short Approximate linear dependence as a design method for Kernel prototype-based classifiers
title_full Approximate linear dependence as a design method for Kernel prototype-based classifiers
title_fullStr Approximate linear dependence as a design method for Kernel prototype-based classifiers
title_full_unstemmed Approximate linear dependence as a design method for Kernel prototype-based classifiers
title_sort Approximate linear dependence as a design method for Kernel prototype-based classifiers
author Coelho, David Nascimento
author_facet Coelho, David Nascimento
Barreto, Guilherme de Alencar
author_role author
author2 Barreto, Guilherme de Alencar
author2_role author
dc.contributor.author.fl_str_mv Coelho, David Nascimento
Barreto, Guilherme de Alencar
dc.subject.por.fl_str_mv Prototype-based classifiers
Sparsification
Approximate linear dependence
Kernel classifiers
Kernel SOM
topic Prototype-based classifiers
Sparsification
Approximate linear dependence
Kernel classifiers
Kernel SOM
description The approximate linear dependence (ALD) method is a sparsification procedure used to build a dictionary of samples extracted from a data set. The extracted samples are approximately linearly independent in a high-dimensional kernel reproducing Hilbert space. In this paper, we argue that the ALD method itself can be used to select relevant prototypes from a training data set and use them to classify new samples using kernelized distances. The results obtained from intensive experimentation with several datasets indicate that the proposed approach is viable to be used as a standalone classifier.
publishDate 2019
dc.date.none.fl_str_mv 2019
2023-02-09T16:49:52Z
2023-02-09T16:49:52Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv COELHO, D. N.; BARRETO, G. A. Approximate linear dependence as a design method for Kernel prototype-based classifiers. In: INTERNATIONAL WORKSHOP ON SELF-ORGANIZING MAPS, 13., 2019, Barcelona. Anais... Barcelona, 2013. p. 241-250.
http://www.repositorio.ufc.br/handle/riufc/70707
identifier_str_mv COELHO, D. N.; BARRETO, G. A. Approximate linear dependence as a design method for Kernel prototype-based classifiers. In: INTERNATIONAL WORKSHOP ON SELF-ORGANIZING MAPS, 13., 2019, Barcelona. Anais... Barcelona, 2013. p. 241-250.
url http://www.repositorio.ufc.br/handle/riufc/70707
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv International Workshop on Self-Organizing Maps
publisher.none.fl_str_mv International Workshop on Self-Organizing Maps
dc.source.none.fl_str_mv reponame:Repositório Institucional da Universidade Federal do Ceará (UFC)
instname:Universidade Federal do Ceará (UFC)
instacron:UFC
instname_str Universidade Federal do Ceará (UFC)
instacron_str UFC
institution UFC
reponame_str Repositório Institucional da Universidade Federal do Ceará (UFC)
collection Repositório Institucional da Universidade Federal do Ceará (UFC)
repository.name.fl_str_mv Repositório Institucional da Universidade Federal do Ceará (UFC) - Universidade Federal do Ceará (UFC)
repository.mail.fl_str_mv bu@ufc.br || repositorio@ufc.br
_version_ 1813028962950971392

Registros relacionados