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.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00019663
Contributor : Pierre Bessiere <>
Submitted on : Tuesday, March 14, 2006 - 10:47:44 AM
Last modification on : Friday, April 12, 2019 - 1:23:58 AM
Document(s) archivé(s) le : Saturday, April 3, 2010 - 8:21:01 PM

Identifiers

  • 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. ⟨hal-00019663⟩

Share

Metrics

Record views

336

Files downloads

217