Supervised and Evolutionary Learning of Echo State Networks

Fei Jiang 1, 2 Hugues Berry 1 Marc Schoenauer 2
1 ALCHEMY - Architectures, Languages and Compilers to Harness the End of Moore Years
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
2 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : A possible alternative to topology fine-tuning for Neural Net- work (NN) optimization is to use Echo State Networks (ESNs), recurrent NNs built upon a large reservoir of sparsely randomly connected neurons. The promises of ESNs have been fulfilled for supervised learning tasks, but unsupervised ones, e.g. control problems, require more flexible optimization methods – such as Evolutionary Algorithms. This paper proposes to apply CMA-ES, the state-of-the-art method in evolutionary continuous parameter optimization, to the evolutionary learning of ESN parameters. First, a standard supervised learning problem is used to validate the approach and compare it to the standard one. But the flexibility of Evolutionary optimization allows us to optimize not only the outgoing weights but also, or alternatively, other ESN parameters, sometimes leading to improved results. The classical double pole balancing control problem is then used to demonstrate the feasibility of evolutionary (i.e. reinforcement) learning of ESNs. We show that the evolutionary ESN obtain results that are comparable with those of the best topology-learning methods.
Type de document :
Communication dans un congrès
International Conference on Parallel Problem Solving From Nature, Sep 2008, Dortmund, Germany. 2008
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00337235
Contributeur : Fei Jiang <>
Soumis le : jeudi 6 novembre 2008 - 14:46:18
Dernière modification le : mercredi 9 mai 2018 - 14:36:03
Document(s) archivé(s) le : mardi 9 octobre 2012 - 15:06:40

Fichier

PPSN08-Jiang.F-Berry.H-Schoena...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00337235, version 1

Collections

Citation

Fei Jiang, Hugues Berry, Marc Schoenauer. Supervised and Evolutionary Learning of Echo State Networks. International Conference on Parallel Problem Solving From Nature, Sep 2008, Dortmund, Germany. 2008. 〈inria-00337235〉

Partager

Métriques

Consultations de la notice

253

Téléchargements de fichiers

979