English

A layered neural network with three-state neurons optimizing the mutual information

Disordered Systems and Neural Networks 2012-08-27 v1 Statistical Mechanics q-bio

Abstract

The time evolution of an exactly solvable layered feedforward neural network with three-state neurons and optimizing the mutual information is studied for arbitrary synaptic noise (temperature). Detailed stationary temperature-capacity and capacity-activity phase diagrams are obtained. The model exhibits pattern retrieval, pattern-fluctuation retrieval and spin-glass phases. It is found that there is an improved performance in the form of both a larger critical capacity and information content compared with three-state Ising-type layered network models. Flow diagrams reveal that saddle-point solutions associated with fluctuation overlaps slow down considerably the flow of the network states towards the stable fixed-points.

Keywords

Cite

@article{arxiv.cond-mat/0305587,
  title  = {A layered neural network with three-state neurons optimizing the mutual information},
  author = {D. Bolle and R. Erichsen, and W. K. Theumann},
  journal= {arXiv preprint arXiv:cond-mat/0305587},
  year   = {2012}
}

Comments

17 pages Latex including 6 eps-figures

R2 v1 2026-07-22T10:50:32.199Z