Title: A layered neural network with three-state neurons optimizing the mutual information
Authors: Bollé, Désiré ×
Erichsen, R
Theumann, WK #
Issue Date: Feb-2004
Series Title: Physica A, Statistical and Theoretical Physics vol:333 pages:516-528
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. (C) 2003 Elsevier B.V. All rights reserved.
ISSN: 0378-4371
Publication status: published
KU Leuven publication type: IT
Appears in Collections:Theoretical Physics Section
× corresponding author
# (joint) last author

Files in This Item:

There are no files associated with this item.

Request a copy


All items in Lirias are protected by copyright, with all rights reserved.

© Web of science