Supervised and Evolutionary Learning of Echo State Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Supervised and Evolutionary Learning of Echo State Networks


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.
Fichier principal
Vignette du fichier
PPSN08-Jiang.F-Berry.H-Schoenauer.M.pdf (143.61 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00337235 , version 1 (06-11-2008)


  • HAL Id : inria-00337235 , version 1


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. ⟨inria-00337235⟩
112 View
694 Download


Gmail Facebook Twitter LinkedIn More