Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators

Autores
Messina, Francisco; Cernuschi Frias, Bruno
Año de publicación
2012
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
All the algorithms for ICA require high-order statistics to estimate the independent components. This is because second-order information is insufficient to assess that two random variables are independent of each other. It is known that the robustness of the high-order sample estimators is poor, meaning that a few outliers can change dramatically its value. In this paper, we generalize the alternative robust statistics for moments and cumulants introduced by Welling [1] presenting the MMSE-robust moments. Then we present a batch and adaptive versions of an algorithm for estimating the parameters that define the estimator. Finally, we modify two FastICA algorithms of ICA based on kurtosis and negentropy to apply the MMSE robust estimators and show some experiments with supergaussian sources to demonstrate the improvement.
Fil: Messina, Francisco. Universidad de Buenos Aires. Facultad de Ingeniería. Departamento de Electronica; Argentina
Fil: Cernuschi Frias, Bruno. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Saavedra 15. Instituto Argentino de Matemática Alberto Calderón; Argentina
41 JAIIO Simposio Argentino de Tecnología (AST 2012)
Buenos Aires
Argentina
Sociedad Argentina de Informática
Universidad Nacional de La Plata
Materia
INDEPENDENT COMPONENT ANALYSIS
ROBUST ALGORITHMS
ADAPTIVE ALGORITHMS
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:11336/157553
Acceder
id CONICETDig_adadce685879769b1db2ae419b2b0bbd
oai_identifier_str oai:ri.conicet.gov.ar:11336/157553
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimatorsMessina, FranciscoCernuschi Frias, BrunoINDEPENDENT COMPONENT ANALYSISROBUST ALGORITHMSADAPTIVE ALGORITHMShttps://purl.org/becyt/ford/2.2https://purl.org/becyt/ford/2All the algorithms for ICA require high-order statistics to estimate the independent components. This is because second-order information is insufficient to assess that two random variables are independent of each other. It is known that the robustness of the high-order sample estimators is poor, meaning that a few outliers can change dramatically its value. In this paper, we generalize the alternative robust statistics for moments and cumulants introduced by Welling [1] presenting the MMSE-robust moments. Then we present a batch and adaptive versions of an algorithm for estimating the parameters that define the estimator. Finally, we modify two FastICA algorithms of ICA based on kurtosis and negentropy to apply the MMSE robust estimators and show some experiments with supergaussian sources to demonstrate the improvement.Fil: Messina, Francisco. Universidad de Buenos Aires. Facultad de Ingeniería. Departamento de Electronica; ArgentinaFil: Cernuschi Frias, Bruno. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Saavedra 15. Instituto Argentino de Matemática Alberto Calderón; Argentina41 JAIIO Simposio Argentino de Tecnología (AST 2012)Buenos AiresArgentinaSociedad Argentina de InformáticaUniversidad Nacional de La PlataUniversidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación2012info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectCongresoJournalhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/157553Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators; 41 JAIIO Simposio Argentino de Tecnología (AST 2012); Buenos Aires; Argentina; 2012; 240-2511850-2806CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://41jaiio.sadio.org.ar/sites/default/files/21_AST_2012.pdfNacionalinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T09:53:02Zoai:ri.conicet.gov.ar:11336/157553instacron: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:34982025-09-29 09:53:02.84CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators
title Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators
spellingShingle Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators
Messina, Francisco
INDEPENDENT COMPONENT ANALYSIS
ROBUST ALGORITHMS
ADAPTIVE ALGORITHMS
title_short Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators
title_full Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators
title_fullStr Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators
title_full_unstemmed Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators
title_sort Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators
dc.creator.none.fl_str_mv Messina, Francisco
Cernuschi Frias, Bruno
author Messina, Francisco
author_facet Messina, Francisco
Cernuschi Frias, Bruno
author_role author
author2 Cernuschi Frias, Bruno
author2_role author
dc.subject.none.fl_str_mv INDEPENDENT COMPONENT ANALYSIS
ROBUST ALGORITHMS
ADAPTIVE ALGORITHMS
topic INDEPENDENT COMPONENT ANALYSIS
ROBUST ALGORITHMS
ADAPTIVE ALGORITHMS
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.2
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv All the algorithms for ICA require high-order statistics to estimate the independent components. This is because second-order information is insufficient to assess that two random variables are independent of each other. It is known that the robustness of the high-order sample estimators is poor, meaning that a few outliers can change dramatically its value. In this paper, we generalize the alternative robust statistics for moments and cumulants introduced by Welling [1] presenting the MMSE-robust moments. Then we present a batch and adaptive versions of an algorithm for estimating the parameters that define the estimator. Finally, we modify two FastICA algorithms of ICA based on kurtosis and negentropy to apply the MMSE robust estimators and show some experiments with supergaussian sources to demonstrate the improvement.
Fil: Messina, Francisco. Universidad de Buenos Aires. Facultad de Ingeniería. Departamento de Electronica; Argentina
Fil: Cernuschi Frias, Bruno. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Saavedra 15. Instituto Argentino de Matemática Alberto Calderón; Argentina
41 JAIIO Simposio Argentino de Tecnología (AST 2012)
Buenos Aires
Argentina
Sociedad Argentina de Informática
Universidad Nacional de La Plata
description All the algorithms for ICA require high-order statistics to estimate the independent components. This is because second-order information is insufficient to assess that two random variables are independent of each other. It is known that the robustness of the high-order sample estimators is poor, meaning that a few outliers can change dramatically its value. In this paper, we generalize the alternative robust statistics for moments and cumulants introduced by Welling [1] presenting the MMSE-robust moments. Then we present a batch and adaptive versions of an algorithm for estimating the parameters that define the estimator. Finally, we modify two FastICA algorithms of ICA based on kurtosis and negentropy to apply the MMSE robust estimators and show some experiments with supergaussian sources to demonstrate the improvement.
publishDate 2012
dc.date.none.fl_str_mv 2012
dc.type.none.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/conferenceObject
Congreso
Journal
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
status_str publishedVersion
format conferenceObject
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/157553
Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators; 41 JAIIO Simposio Argentino de Tecnología (AST 2012); Buenos Aires; Argentina; 2012; 240-251
1850-2806
CONICET Digital
CONICET
url http://hdl.handle.net/11336/157553
identifier_str_mv Robust parallel fast-ICA algorithms using batch and adaptive MMSE estimators; 41 JAIIO Simposio Argentino de Tecnología (AST 2012); Buenos Aires; Argentina; 2012; 240-251
1850-2806
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://41jaiio.sadio.org.ar/sites/default/files/21_AST_2012.pdf
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
dc.coverage.none.fl_str_mv Nacional
dc.publisher.none.fl_str_mv Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación
publisher.none.fl_str_mv Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación
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_ 1844613624425873408
score 13.070432

Publicaciones similares