Making competition in neural fields suitable for computational architectures

  • Authors:
  • Hervé Frezza-Buet;Olivier Ménard

  • Affiliations:
  • Supélec, Metz, France;Supélec, Metz, France

  • Venue:
  • ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, a new competition mechanism for neural fields is proposed, as well as first experimental studies of its robustness. The computational properties of this algorithm are discussed, arguing that such properties are suitable for neural architectures, where some restrictions of the usual neural fields competition methods are not acceptable.