Optimal Transport Applied to Transfer Learning For P300 Detection

Abstract : Brain Computer Interfaces suffer from considerable cross-session and cross-subject variability, which makes it hard for classification methods to generalize. We introduce a transfer learning method based on regularized discrete optimal transport with class labels in the interest of enhancing the generalization capacity of state-of-the-art classification methods. We demonstrate the potential of this approach by applying it to offline cross-subject transfer learning for the P300-Speller paradigm. We also simulate an online experiment to assess the feasibility of our method. Results show that our method is comparable to-and sometimes even outperforms-session-dependent classification.
Type de document :
Communication dans un congrès
BCI 2017 - 7th Graz Brain-Computer Interface Conference, Sep 2017, Graz, Austria. pp.6
Liste complète des métadonnées

Littérature citée [21 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01556603
Contributeur : Nathalie Thérèse Hélène Gayraud <>
Soumis le : mercredi 5 juillet 2017 - 12:17:27
Dernière modification le : lundi 25 septembre 2017 - 09:48:28

Fichier

GBCIC_2017_paper_75.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01556603, version 1

Collections

Citation

Nathalie T. H. Gayraud, Alain Rakotomamonjy, Maureen Clerc. Optimal Transport Applied to Transfer Learning For P300 Detection. BCI 2017 - 7th Graz Brain-Computer Interface Conference, Sep 2017, Graz, Austria. pp.6. 〈hal-01556603〉

Partager

Métriques

Consultations de la notice

235

Téléchargements de fichiers

86