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