Skip to Main content Skip to Navigation
Conference papers

New conditioning model for robots

Jean-Marc Salotti 1, *
* Corresponding author
1 COGNITIQUE
IMS - Laboratoire de l'intégration, du matériau au système
Abstract : We present a neural network for the prediction of rewards in a conditioning model. It is based on two noisy-or and one noisy-and nodes and update rules inspired from BANNER technique. In specific cases, we show that the computation is similar to Rescorla-Wagner's equation, which inspired many computational models in the domain of conditioning
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00669961
Contributor : Nelly Troadec <>
Submitted on : Tuesday, February 14, 2012 - 11:31:50 AM
Last modification on : Thursday, February 7, 2019 - 2:22:36 PM
Document(s) archivé(s) le : Tuesday, May 15, 2012 - 2:35:10 AM

File

version_finale_ESANN2011-104_1...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00669961, version 1

Citation

Jean-Marc Salotti. New conditioning model for robots. New conditioning model for robots, Apr 2011, Bruges, Belgium. pp.147-152. ⟨hal-00669961⟩

Share

Metrics

Record views

137

Files downloads

99