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

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

2003-05-26

arxiv.org/abs/cond-mat/0305587v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

17 pages Latex including 6 eps-figures

Scientific paper

10.1016/j.physa.2003.10.033

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.

Affiliated with

Also associated with

No associations

Rating

A layered neural network with three-state neurons optimizing the mutual information does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A layered neural network with three-state neurons optimizing the mutual information, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A layered neural network with three-state neurons optimizing the mutual information will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-457637