Bistable Gradient Networks in the Thermodynamic Limit

Details Bistable Gradient Networks in the Thermodynamic Limit Bistable Gradient Networks in the Thermodynamic Limit

2002-03-27

arxiv.org/abs/cond-mat/0203568v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

RevTeX, 18 pages including 12 figures. Submitted to Phys. Rev. E

Scientific paper

We examine the large-network, low-loading behaviour of an attractor neural network, the so-called bistable gradient network (BGN). We use analytical and numerical methods to characterize the attractor states of the network and their basins of attraction. The energy landscape is more complex than that of the Hopfield network and depends on the strength of the coupling among units. At weak coupling, the BGN acts as a highly selective associative memory; the input must be close to the one of the stored patterns in order to be recognized. A category of spurious attractors occurs which is not present in the Hopfield network. Stronger coupling results in a transition to a more Hopfield-like regime with large basins of attraction. The basins of attraction for spurious attractors are noticeably suppressed compared to the Hopfield case, even though the Hebbian synaptic structure is the same and there is no stochastic noise.

Affiliated with

Also associated with

No associations

Rating

Bistable Gradient Networks in the Thermodynamic Limit 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 Bistable Gradient Networks in the Thermodynamic Limit, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Bistable Gradient Networks in the Thermodynamic Limit will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-237902