Structure and dynamics of random recurrent neural networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Adaptive Behavior Year : 2006

Structure and dynamics of random recurrent neural networks

Abstract

In contradiction with Hopfield-like networks, random recurrent neural networks (RRNN), where the couplings are random, exhibit complex dynamics (limit cycles, chaos). It is possible to store information in these netwoks through hebbian learning. Eventually, learning ``destroys'' the dynamics and leads to a fixed point attractor. We investigate here the structural change in the networks through learning, and show a ``small-world'' effect.
Fichier principal
Vignette du fichier
DSaLC_Berry_Quoy.pdf (836.26 Ko) Télécharger le fichier
Loading...

Dates and versions

inria-00001065 , version 1 (29-01-2006)

Identifiers

  • HAL Id : inria-00001065 , version 1

Cite

Hugues Berry, Mathias Quoy. Structure and dynamics of random recurrent neural networks. Adaptive Behavior, 2006, 14, pp.129-137. ⟨inria-00001065⟩
211 View
351 Download

Share

Gmail Facebook X LinkedIn More