Automatic synthesis of working memory neural networks with neuroevolution methods - Archive ouverte HAL Access content directly
Conference Papers Year :

Automatic synthesis of working memory neural networks with neuroevolution methods

Abstract

Evolutionary Robotics is a research field focused on autonomous design of robots based on evolutionary algorithms. In this field, neuroevolution methods aims in particular at designing both structure and parameters of neural networks that make a robot exhibit a desired behavior. While such methods have shown their efficiency to generate reactive behaviors, they hardly scale to more cognitive behaviors. One of the reasons of such a limitation might be in the properties of the encoding, i.e. the neural network representation explored by the genetic operators. This work considers EvoNeuro encoding, an encoding directly inspired from computational neuroscience and tests its efficiency on a working memory task, namely the AX-CPT task. Neural networks able to solve this task are generated and compared to neural networks evolved with a simpler direct encoding. The task is solved in both cases, but while direct encodings tend to generate networks whose structure is adapted to a particular instance of AX-CPT, networks generated with EvoNeuro encoding are more versatile and can adapt to the new task through a simple parameter optimization. Such versatile neural networks might facilitate the evolution of robot controllers for tasks requiring a working memory.
Fichier principal
Vignette du fichier
NEUROCOMP2010_0010_e2c6cbd58354e5f897c86a79082a372f.pdf (608.7 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00553407 , version 1 (10-03-2011)

Identifiers

  • HAL Id : hal-00553407 , version 1

Cite

Tony Pinville, Stéphane Doncieux. Automatic synthesis of working memory neural networks with neuroevolution methods. Cinquième conférence plénière française de Neurosciences Computationnelles, "Neurocomp'10", Aug 2010, Lyon, France. ⟨hal-00553407⟩
86 View
57 Download

Share

Gmail Facebook Twitter LinkedIn More