Unsupervised Learning of Echo State Networks: A case study in Artificial Embryogeny.

Alexandre Devert 1 Nicolas Bredeche 1, 2 Marc Schoenauer 1
1 TANC - Algorithmic number theory for cryptology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France, X - École polytechnique, CNRS - Centre National de la Recherche Scientifique : UMR7161
Abstract : Echo State Networks (ESN) have demonstrated their efficiency in supervised learning of time series: a "reservoir" of neurons provide a set of dynamical systems that can be linearly combined to match the target dynamics, using a simple quadratic optimisation algorithm to tune the few free parameters. In an unsupervised learning context, however, another optimiser is needed. In this paper, an adaptive (1+1)-Evolution Strategy as well as the state-of-the-art CMA-ES are used to optimise an ESN to tackle the "flag" problem, a classical benchmark from multi-cellular artificial embryogeny: the genotype is the cell controller of a Continuous Cellular Automata, and the phenotype, the image that corresponds to the fixed point of the resulting dynamical system, must match a given 2D pattern. This approach is able to provide excellent results with few evaluations, and favourably compares to that using the NEAT algorithm (a state-of-the-art neuro-evolution method) to evolve the cell controllers. Some characteristics of the fitness landscape of the ESN-based method are also investigated.
Document type :
Conference papers
Nicolas Monmarché and Talbi El-Ghazali and Pierre Collet and Marc Schoenauer and Evelyne Lutton. Evolution Artificielle, Oct 2007, Tours, France. 4926, pp.278-290, 2007, Lecture Notes in Computer Science
Liste complète des métadonnées

Cited literature [32 references]  Display  Hide  Download

https://hal.inria.fr/inria-00174593
Contributor : Nicolas Bredeche <>
Submitted on : Monday, September 24, 2007 - 5:08:04 PM
Last modification on : Thursday, May 10, 2018 - 2:07:00 AM
Document(s) archivé(s) le : Friday, April 9, 2010 - 2:45:54 AM

File

EA2007esndev.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00174593, version 1

Collections

Citation

Alexandre Devert, Nicolas Bredeche, Marc Schoenauer. Unsupervised Learning of Echo State Networks: A case study in Artificial Embryogeny.. Nicolas Monmarché and Talbi El-Ghazali and Pierre Collet and Marc Schoenauer and Evelyne Lutton. Evolution Artificielle, Oct 2007, Tours, France. 4926, pp.278-290, 2007, Lecture Notes in Computer Science. 〈inria-00174593〉

Share

Metrics

Record views

366

Files downloads

1067