Sensorimotor learning in a Bayesian computational model of speech communication

Abstract : Although sensorimotor exploration is a basic process within child development, clear views on the underlying computational processes remain challenging. We propose to compare eight algorithms for sensorimotor exploration, based on three components: " accommodation " performing a compromise between goal babbling and social guidance by a master, " local extrapolation " simulating local exploration of the sensorimotor space to achieve motor generalizations and " idiosyncratic babbling " which favors already explored motor commands when they are efficient. We will show that a mix of these three components offers a good compromise enabling efficient learning while reducing exploration as much as possible.
Type de document :
Communication dans un congrès
The Sixth Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB 2016), Sep 2016, Cergy-Pontoise, France. 〈http://www.icdl-epirob.org/〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01371719
Contributeur : Marie-Lou Barnaud <>
Soumis le : mardi 27 septembre 2016 - 14:02:48
Dernière modification le : lundi 9 avril 2018 - 12:22:49
Document(s) archivé(s) le : mercredi 28 décembre 2016 - 12:29:40

Fichier

epirob-icdl_2016.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01371719, version 1

Collections

Citation

Marie-Lou Barnaud, Jean-Luc Schwartz, Julien Diard, Pierre Bessière. Sensorimotor learning in a Bayesian computational model of speech communication. The Sixth Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB 2016), Sep 2016, Cergy-Pontoise, France. 〈http://www.icdl-epirob.org/〉. 〈hal-01371719〉

Partager

Métriques

Consultations de la notice

358

Téléchargements de fichiers

87