Multiple Operator-valued Kernel Learning - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Rapport (Rapport De Recherche) Année : 2012

Multiple Operator-valued Kernel Learning

Résumé

This paper addresses the problem of learning a finite linear combination of operator-valued kernels. We study this problem in the case of kernel ridge regression for functional responses with a lr-norm constraint on the combination coefficients. We propose a multiple operator-valued kernel learning algorithm based on solving a system of linear operator equations by using a block coordinate descent procedure. We experimentally validate our approach on a functional regression task in the context of finger movement prediction in Brain-Computer Interface (BCI).
Fichier principal
Vignette du fichier
RR-7900.pdf (285.22 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00677012 , version 1 (07-03-2012)
hal-00677012 , version 2 (14-06-2012)

Identifiants

Citer

Hachem Kadri, Alain Rakotomamonjy, Francis Bach, Philippe Preux. Multiple Operator-valued Kernel Learning. [Research Report] RR-7900, 2012. ⟨hal-00677012v1⟩

Collections

INRIA-RRRT
500 Consultations
741 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More