Auto-supervised learning in the Bayesian Programming Framework

Pierre Dangauthier 1 Pierre Bessiere 1 Anne Spalanzani 1
1 E-MOTION - Geometry and Probability for Motion and Action
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes
Abstract : Domestic and real world robotics requires continuous learning of new skills and behaviors to interact with humans. Auto-supervised learning, a compromise between supervised and completely unsupervised learning, consist in relying on previous knowledge to acquire new skills. We propose here to realize auto-supervised learning by exploiting statistical regularities in the sensorimotor space of a robot. In our context, it corresponds to achieve feature selection in a Bayesian programming framework. We compare several feature selection algorithms and validate them on a real robotic experiment.
Type de document :
Communication dans un congrès
2005, pp.1-6, 2005
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00019663
Contributeur : Pierre Bessiere <>
Soumis le : mardi 14 mars 2006 - 10:47:44
Dernière modification le : mercredi 17 janvier 2018 - 10:44:41
Document(s) archivé(s) le : samedi 3 avril 2010 - 20:21:01

Identifiants

  • HAL Id : hal-00019663, version 1

Collections

INRIA | UGA | IMAG

Citation

Pierre Dangauthier, Pierre Bessiere, Anne Spalanzani. Auto-supervised learning in the Bayesian Programming Framework. 2005, pp.1-6, 2005. 〈hal-00019663〉

Partager

Métriques

Consultations de la notice

329

Téléchargements de fichiers

203