Unsupervised feature extraction via kernel subspace techniques
Autor(a) principal: | |
---|---|
Data de Publicação: | 2011 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.26/47400 |
Resumo: | This paper provides a new insight into unsupervised feature extraction techniques based on kernel subspace models. The data projected onto kernel subspace models are new data representations which might be better suited for classification. The kernel subspace models are always described exploiting the dual form for the basis vectors which requires that the training data must be available even during the test phase. By exploiting an incomplete Cholesky decomposition of the kernel matrix, a computationally less demanding implementation is proposed. Online benchmark data sets allow the evaluation of these feature extraction methods comparing the performance of two classifiers which both have as input either the raw data or the new representations. |
id |
RCAP_a779d51bd201c50294c635e6b3c56054 |
---|---|
oai_identifier_str |
oai:comum.rcaap.pt:10400.26/47400 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Unsupervised feature extraction via kernel subspace techniquesKernel PCAFeature extraction and low-rank decompositionsThis paper provides a new insight into unsupervised feature extraction techniques based on kernel subspace models. The data projected onto kernel subspace models are new data representations which might be better suited for classification. The kernel subspace models are always described exploiting the dual form for the basis vectors which requires that the training data must be available even during the test phase. By exploiting an incomplete Cholesky decomposition of the kernel matrix, a computationally less demanding implementation is proposed. Online benchmark data sets allow the evaluation of these feature extraction methods comparing the performance of two classifiers which both have as input either the raw data or the new representations.[IADIS]Repositório ComumTeixeira, A.R.Tomé, A.M.Lang, E.W.2023-10-23T11:23:14Z20112011-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.26/47400eng10.1016/j.neucom.2010.11.011info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-10-26T02:16:28Zoai:comum.rcaap.pt:10400.26/47400Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:39:34.371660Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Unsupervised feature extraction via kernel subspace techniques |
title |
Unsupervised feature extraction via kernel subspace techniques |
spellingShingle |
Unsupervised feature extraction via kernel subspace techniques Teixeira, A.R. Kernel PCA Feature extraction and low-rank decompositions |
title_short |
Unsupervised feature extraction via kernel subspace techniques |
title_full |
Unsupervised feature extraction via kernel subspace techniques |
title_fullStr |
Unsupervised feature extraction via kernel subspace techniques |
title_full_unstemmed |
Unsupervised feature extraction via kernel subspace techniques |
title_sort |
Unsupervised feature extraction via kernel subspace techniques |
author |
Teixeira, A.R. |
author_facet |
Teixeira, A.R. Tomé, A.M. Lang, E.W. |
author_role |
author |
author2 |
Tomé, A.M. Lang, E.W. |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Repositório Comum |
dc.contributor.author.fl_str_mv |
Teixeira, A.R. Tomé, A.M. Lang, E.W. |
dc.subject.por.fl_str_mv |
Kernel PCA Feature extraction and low-rank decompositions |
topic |
Kernel PCA Feature extraction and low-rank decompositions |
description |
This paper provides a new insight into unsupervised feature extraction techniques based on kernel subspace models. The data projected onto kernel subspace models are new data representations which might be better suited for classification. The kernel subspace models are always described exploiting the dual form for the basis vectors which requires that the training data must be available even during the test phase. By exploiting an incomplete Cholesky decomposition of the kernel matrix, a computationally less demanding implementation is proposed. Online benchmark data sets allow the evaluation of these feature extraction methods comparing the performance of two classifiers which both have as input either the raw data or the new representations. |
publishDate |
2011 |
dc.date.none.fl_str_mv |
2011 2011-01-01T00:00:00Z 2023-10-23T11:23:14Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.26/47400 |
url |
http://hdl.handle.net/10400.26/47400 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1016/j.neucom.2010.11.011 |
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 |
[IADIS] |
publisher.none.fl_str_mv |
[IADIS] |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133657188794368 |