Multimodal Sequence Learning with a Cortically-Inspired Model - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 1998

Multimodal Sequence Learning with a Cortically-Inspired Model

Hervé Frezza-Buet
Frédéric Alexandre

Résumé

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.
Fichier principal
Vignette du fichier
98-R-237.pdf (186.38 Ko) Télécharger le fichier

Dates et versions

inria-00098710 , version 1 (26-09-2006)

Identifiants

  • HAL Id : inria-00098710 , version 1

Citer

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, pp.24-27. ⟨inria-00098710⟩
81 Consultations
50 Téléchargements

Partager

Gmail Facebook X LinkedIn More