Feature Selection For Self-Supervised Learning

Pierre Dangauthier 1 Pierre Bessiere Anne Spalanzani
1 E-MOTION - Geometry and Probability for Motion and Action
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes
Abstract : A foundation of the developmental approach to robotics is that learning must be grounded on sensorimotor interaction. In order to behave autonomously, a robot has to build its own model of the world by searching and exploiting statistical regularities in his sensorimotor domain. Self-supervised learning consists in relying on previous knowledge to acquire new skills. We propose to mix self-supervised learning with our probabilistic programming method, the Bayesian Robot Programming Framework. This idea corresponds to achieve feature selection for searching for relevant sensors. We compare several feature selection algorithms and validate them on a real robotic experiment
Document type :
Reports
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/inria-00182037
Contributor : Christian Laugier <>
Submitted on : Wednesday, October 24, 2007 - 6:33:41 PM
Last modification on : Thursday, April 11, 2019 - 12:04:12 PM
Long-term archiving on : Monday, April 12, 2010 - 12:31:42 AM

File

dangauthier05devrob.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00182037, version 1

Collections

INRIA | UGA | LARA | IMAG

Citation

Pierre Dangauthier, Pierre Bessiere, Anne Spalanzani. Feature Selection For Self-Supervised Learning. [Technical Report] 2005. ⟨inria-00182037⟩

Share

Metrics

Record views

344

Files downloads

289