Unsupervised Learning of Echo State Networks: A case study in Artificial Embryogeny. - Archive ouverte HAL Access content directly
Conference Papers Year : 2007

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

(1) , (1, 2) , (1)
1
2

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.
Fichier principal
Vignette du fichier
EA2007esndev.pdf (206.03 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00174593 , version 1 (24-09-2007)

Identifiers

  • HAL Id : inria-00174593 , version 1

Cite

Alexandre Devert, Nicolas Bredeche, Marc Schoenauer. Unsupervised Learning of Echo State Networks: A case study in Artificial Embryogeny.. Evolution Artificielle, Oct 2007, Tours, France. pp.278-290. ⟨inria-00174593⟩
346 View
643 Download

Share

Gmail Facebook Twitter LinkedIn More