Multimodal Sequence Learning with a Cortically-Inspired Model

Hervé Frezza-Buet 1 Frédéric Alexandre 1
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We present in this paper a cortically-inspired model that learns to exploit regularities of sequences of perceptions and actions, with regard to motivations. Sequences are learned from continuous multimodal information streams, on the basis of a competition mechanism. This approach enables generalisations from perceptive regularities and also ensures the capability to apply results of previous learning to help further learning of new tasks.
Type de document :
Communication dans un congrès
3nd International Conference on Computational Intelligence & Neuroscience - JCIS'98 - Association for Intelligent Machinery, 1998, none, 2, pp.24-27, 1998
Liste complète des métadonnées

https://hal.inria.fr/inria-00098710
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 08:18:46
Dernière modification le : jeudi 11 janvier 2018 - 06:19:48
Document(s) archivé(s) le : mercredi 29 mars 2017 - 12:29:10

Fichiers

Identifiants

  • HAL Id : inria-00098710, version 1

Collections

Citation

Hervé Frezza-Buet, Frédéric Alexandre. Multimodal Sequence Learning with a Cortically-Inspired Model. 3nd International Conference on Computational Intelligence & Neuroscience - JCIS'98 - Association for Intelligent Machinery, 1998, none, 2, pp.24-27, 1998. 〈inria-00098710〉

Partager

Métriques

Consultations de la notice

233

Téléchargements de fichiers

27