Transient dynamics for sequence processing neural networks: effect of degree distributions

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We derive a analytic evolution equation for overlap parameters including the effect of degree distribution on the transient dynamics of sequence processing neural networks. In the special case of globally coupled networks, the precisely retrieved critical loading ratio $α_c = N ^{-1/2}$ is obtained, where $N$ is the network size. In the presence of random networks, our theoretical predictions agree quantitatively with the numerical experiments for delta, binomial, and power-law degree distributions.
11 pages, 6 figures

Keywords

Disordered Systems and Neural Networks, Statistical Mechanics

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/146874

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/0705.3679
 http://arxiv.org/abs/0705.3679
 Phys. Rev. E 77, 016110 (2008)
 doi:10.1103/PhysRevE.77.016110

Collections

arXiv