Selecting from an infinite set of features in SVM

Rémi Flamary; Florian Yger; Alain Rakotomamonjy

Selecting from an infinite set of features in SVM

Rémi Flamary
, Florian Yger
, Alain Rakotomamonjy

LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collection › Contribution à une conférence › Revue par des pairs

Résumé

Dealing with the continuous parameters of a feature extraction method has always been a difficult task that is usually solved by cross-validation. In this paper, we propose an active set algorithm for selecting automatically these parameters in a SVM classification context. Our experiments on texture recognition and BCI signal classification show that optimizing the feature parameters in a continuous space while learning the decision function yields to better performances than using fixed parameters obtained from a grid sampling.

langue originale	Anglais
titre	Proceedings of the 19th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2011
Editeur	ESANN (i6doc.com)
Pages	327-332
Nombre de pages	6
ISBN (Electronique)	9782874190445
état	Publié - 1 janv. 2011
Modification externe	Oui
Evénement	19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2011 - Bruges, Belgique Durée: 27 avr. 2011 → 29 avr. 2011

Série de publications

Nom	ESANN 2011 - 19th European Symposium on Artificial Neural Networks

Une conférence

Une conférence	19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2011
Pays/Territoire	Belgique
La ville	Bruges
période	27/04/11 → 29/04/11

Contient cette citation

@inproceedings{42e55ed765a448a7a6f637bb9188de62,

title = "Selecting from an infinite set of features in SVM",

abstract = "Dealing with the continuous parameters of a feature extraction method has always been a difficult task that is usually solved by cross-validation. In this paper, we propose an active set algorithm for selecting automatically these parameters in a SVM classification context. Our experiments on texture recognition and BCI signal classification show that optimizing the feature parameters in a continuous space while learning the decision function yields to better performances than using fixed parameters obtained from a grid sampling.",

author = "R{\'e}mi Flamary and Florian Yger and Alain Rakotomamonjy",

note = "Publisher Copyright: {\textcopyright} European Symposium on Artificial Neural Networks. All rights reserved.; 19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2011 ; Conference date: 27-04-2011 Through 29-04-2011",

year = "2011",

month = jan,

day = "1",

language = "English",

series = "ESANN 2011 - 19th European Symposium on Artificial Neural Networks",

publisher = "ESANN (i6doc.com)",

pages = "327--332",

booktitle = "Proceedings of the 19th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2011",

}

Flamary, R, Yger, F & Rakotomamonjy, A 2011, Selecting from an infinite set of features in SVM. Dans Proceedings of the 19th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2011. ESANN 2011 - 19th European Symposium on Artificial Neural Networks, ESANN (i6doc.com), p. 327-332, 19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2011, Bruges, Belgique, 27/04/11.

Selecting from an infinite set of features in SVM. / Flamary, Rémi; Yger, Florian; Rakotomamonjy, Alain.
Proceedings of the 19th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2011. ESANN (i6doc.com), 2011. p. 327-332 (ESANN 2011 - 19th European Symposium on Artificial Neural Networks).

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collection › Contribution à une conférence › Revue par des pairs

TY - GEN

T1 - Selecting from an infinite set of features in SVM

AU - Flamary, Rémi

AU - Yger, Florian

AU - Rakotomamonjy, Alain

PY - 2011/1/1

Y1 - 2011/1/1

N2 - Dealing with the continuous parameters of a feature extraction method has always been a difficult task that is usually solved by cross-validation. In this paper, we propose an active set algorithm for selecting automatically these parameters in a SVM classification context. Our experiments on texture recognition and BCI signal classification show that optimizing the feature parameters in a continuous space while learning the decision function yields to better performances than using fixed parameters obtained from a grid sampling.

AB - Dealing with the continuous parameters of a feature extraction method has always been a difficult task that is usually solved by cross-validation. In this paper, we propose an active set algorithm for selecting automatically these parameters in a SVM classification context. Our experiments on texture recognition and BCI signal classification show that optimizing the feature parameters in a continuous space while learning the decision function yields to better performances than using fixed parameters obtained from a grid sampling.

M3 - Conference contribution

AN - SCOPUS:85088915494

T3 - ESANN 2011 - 19th European Symposium on Artificial Neural Networks

SP - 327

EP - 332

BT - Proceedings of the 19th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2011

PB - ESANN (i6doc.com)

T2 - 19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2011

Y2 - 27 April 2011 through 29 April 2011

ER -

Selecting from an infinite set of features in SVM

Résumé

Série de publications

Une conférence

Empreinte digitale

Contient cette citation