English

Parallel dynamics of fully connected Q-Ising neural networks

Disordered Systems and Neural Networks 2019-08-15 v1

Abstract

Using a probabilistic approach we study the parallel dynamics of fully connected Q-Ising neural networks for arbitrary Q. A Lyapunov function is shown to exist at zero temperature. A recursive scheme is set up to determine the time evolution of the order parameters through the evolution of the distribution of the local field. As an illustrative example, an explicit analysis is carried out for the first three time steps. For the case of the Q=3 model these theoretical results are compared with extensive numerical simulations. Finally, equilibrium fixed-point equations are derived and compared with the thermodynamic approach based upon the replica-symmetric mean-field approximation.

Keywords

Cite

@article{arxiv.cond-mat/9704089,
  title  = {Parallel dynamics of fully connected Q-Ising neural networks},
  author = {D. Bollé and G. Jongen and G. M. Shim},
  journal= {arXiv preprint arXiv:cond-mat/9704089},
  year   = {2019}
}

Comments

26 pages incl. figures, LaTeX, uses rotate.sty and epsfig.sty

R2 v1 2026-07-22T11:57:14.625Z