HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

Structure and dynamics of random recurrent neural networks

Hugues Berry 1 Mathias Quoy 2
1 ALCHEMY - Architectures, Languages and Compilers to Harness the End of Moore Years
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France
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.
Complete list of metadata

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/inria-00001065
Contributor : Hugues Berry Connect in order to contact the contributor
Submitted on : Sunday, January 29, 2006 - 7:46:58 PM
Last modification on : Friday, February 4, 2022 - 3:30:13 AM
Long-term archiving on: : Saturday, April 3, 2010 - 9:57:24 PM

Identifiers

  • HAL Id : inria-00001065, version 1

Citation

Hugues Berry, Mathias Quoy. Structure and dynamics of random recurrent neural networks. Adaptive Behavior, SAGE Publications, 2006, pp.129-137. ⟨inria-00001065⟩

Share

Metrics

Record views

200

Files downloads

297