Learning kernels for support vector machines with polynomial powers of sigmoid
Autor(a) principal: | |
---|---|
Data de Publicação: | 2014 |
Outros Autores: | , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6915316 http://hdl.handle.net/11449/130175 |
Resumo: | In the pattern recognition research field, Support Vector Machines (SVM) have been an effectiveness tool for classification purposes, being successively employed in many applications. The SVM input data is transformed into a high dimensional space using some kernel functions where linear separation is more likely. However, there are some computational drawbacks associated to SVM. One of them is the computational burden required to find out the more adequate parameters for the kernel mapping considering each non-linearly separable input data space, which reflects the performance of SVM. This paper introduces the Polynomial Powers of Sigmoid for SVM kernel mapping, and it shows their advantages over well-known kernel functions using real and synthetic datasets. |
id |
UNSP_21ce7662e39961272803f58022a5e8b3 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/130175 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Learning kernels for support vector machines with polynomial powers of sigmoidMachine learningKernel functionsPolynomial powers of sigmoidPPS-RadialSupport vector machinesIn the pattern recognition research field, Support Vector Machines (SVM) have been an effectiveness tool for classification purposes, being successively employed in many applications. The SVM input data is transformed into a high dimensional space using some kernel functions where linear separation is more likely. However, there are some computational drawbacks associated to SVM. One of them is the computational burden required to find out the more adequate parameters for the kernel mapping considering each non-linearly separable input data space, which reflects the performance of SVM. This paper introduces the Polynomial Powers of Sigmoid for SVM kernel mapping, and it shows their advantages over well-known kernel functions using real and synthetic datasets.Department of Computing, UFSCar - Federal University of Sao Carlos, São Carlos - SP, Brazil.Department of Computing, UNEMAT - Univ State of Mato Grosso, Alto Araguaia - MT, Brazil.Institute of Computing, University of Campinas, Campinas - SP, Brazil.Universidade Estadual Paulista, Department of Computing, Bauru - SP, Brazil.IeeeUniversidade Federal de São Carlos (UFSCar)Universidade do Estado de Mato Grosso (UNEMAT)Universidade Estadual de Campinas (UNICAMP)Universidade Estadual Paulista (Unesp)Fernandes, Silas E. N.Pilastri, Andre LuizPereira, Luis A. M.Pires, Rafael G. [UNESP]Papa, João P. [UNESP]2015-11-03T15:29:57Z2015-11-03T15:29:57Z2014-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject259-265http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=69153162014 27th Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi). New York: Ieee, p. 259-265, 2014.http://hdl.handle.net/11449/13017510.1109/SIBGRAPI.2014.36WOS:000352613900034Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2014 27th Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi)info:eu-repo/semantics/openAccess2024-04-23T16:11:19Zoai:repositorio.unesp.br:11449/130175Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:18:34.628847Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Learning kernels for support vector machines with polynomial powers of sigmoid |
title |
Learning kernels for support vector machines with polynomial powers of sigmoid |
spellingShingle |
Learning kernels for support vector machines with polynomial powers of sigmoid Fernandes, Silas E. N. Machine learning Kernel functions Polynomial powers of sigmoid PPS-Radial Support vector machines |
title_short |
Learning kernels for support vector machines with polynomial powers of sigmoid |
title_full |
Learning kernels for support vector machines with polynomial powers of sigmoid |
title_fullStr |
Learning kernels for support vector machines with polynomial powers of sigmoid |
title_full_unstemmed |
Learning kernels for support vector machines with polynomial powers of sigmoid |
title_sort |
Learning kernels for support vector machines with polynomial powers of sigmoid |
author |
Fernandes, Silas E. N. |
author_facet |
Fernandes, Silas E. N. Pilastri, Andre Luiz Pereira, Luis A. M. Pires, Rafael G. [UNESP] Papa, João P. [UNESP] |
author_role |
author |
author2 |
Pilastri, Andre Luiz Pereira, Luis A. M. Pires, Rafael G. [UNESP] Papa, João P. [UNESP] |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de São Carlos (UFSCar) Universidade do Estado de Mato Grosso (UNEMAT) Universidade Estadual de Campinas (UNICAMP) Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Fernandes, Silas E. N. Pilastri, Andre Luiz Pereira, Luis A. M. Pires, Rafael G. [UNESP] Papa, João P. [UNESP] |
dc.subject.por.fl_str_mv |
Machine learning Kernel functions Polynomial powers of sigmoid PPS-Radial Support vector machines |
topic |
Machine learning Kernel functions Polynomial powers of sigmoid PPS-Radial Support vector machines |
description |
In the pattern recognition research field, Support Vector Machines (SVM) have been an effectiveness tool for classification purposes, being successively employed in many applications. The SVM input data is transformed into a high dimensional space using some kernel functions where linear separation is more likely. However, there are some computational drawbacks associated to SVM. One of them is the computational burden required to find out the more adequate parameters for the kernel mapping considering each non-linearly separable input data space, which reflects the performance of SVM. This paper introduces the Polynomial Powers of Sigmoid for SVM kernel mapping, and it shows their advantages over well-known kernel functions using real and synthetic datasets. |
publishDate |
2014 |
dc.date.none.fl_str_mv |
2014-01-01 2015-11-03T15:29:57Z 2015-11-03T15:29:57Z |
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 |
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6915316 2014 27th Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi). New York: Ieee, p. 259-265, 2014. http://hdl.handle.net/11449/130175 10.1109/SIBGRAPI.2014.36 WOS:000352613900034 |
url |
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6915316 http://hdl.handle.net/11449/130175 |
identifier_str_mv |
2014 27th Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi). New York: Ieee, p. 259-265, 2014. 10.1109/SIBGRAPI.2014.36 WOS:000352613900034 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2014 27th Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi) |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
259-265 |
dc.publisher.none.fl_str_mv |
Ieee |
publisher.none.fl_str_mv |
Ieee |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128631527964672 |