Jitter-Adaptive Dictionary Learning -Application to Multi-Trial Neuroelectric Signals

Abstract : Dictionary Learning has proven to be a powerful tool for many image processing tasks, where atoms are typically defined on small image patches. As a drawback, the dictionary only encodes basic structures. In addition, this approach treats patches of different locations in one single set, which means a loss of informa-tion when features are well-aligned across signals. This is the case, for instance, in multi-trial magneto-or electroencephalography (M/EEG). Learning the dictio-nary on the entire signals could make use of the alignment and reveal higher-level features. In this case, however, small misalignments or phase variations of fea-tures would not be compensated for. In this paper, we propose an extension to the common dictionary learning framework to overcome these limitations by allowing atoms to adapt their position across signals. The method is validated on simulated and real neuroelectric data.
Type de document :
Communication dans un congrès
ICLR - 1st International Conference on Learning Representations - 2013, May 2013, Phoenix, Arizona, United States. 2013, <https://sites.google.com/site/representationlearning2013/>
Liste complète des métadonnées


https://hal.inria.fr/hal-01094619
Contributeur : Sebastian Hitziger <>
Soumis le : vendredi 19 décembre 2014 - 15:11:29
Dernière modification le : jeudi 9 février 2017 - 15:02:48
Document(s) archivé(s) le : samedi 15 avril 2017 - 08:19:00

Fichier

1301.3611(1).pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01094619, version 1
  • ARXIV : 1301.3611

Citation

Sebastian Hitziger, Maureen Clerc, Alexandre Gramfort, Sandrine Saillet, Christian Bénar, et al.. Jitter-Adaptive Dictionary Learning -Application to Multi-Trial Neuroelectric Signals. ICLR - 1st International Conference on Learning Representations - 2013, May 2013, Phoenix, Arizona, United States. 2013, <https://sites.google.com/site/representationlearning2013/>. <hal-01094619>

Partager

Métriques

Consultations de
la notice

1781

Téléchargements du document

103