Bistable Gradient Networks II: Storage Capacity and Behaviour Near Saturation

Details Bistable Gradient Networks II: Storage Capacity and Behaviour Near Saturation Bistable Gradient Networks II: Storage Capacity and Behaviour Near Saturation

2002-05-23

arxiv.org/abs/cond-mat/0205465v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

15 pages, 12 eps figures. Submitted to Phys. Rev. E. Sequel to cond-mat/0203568

Scientific paper

10.1103/PhysRevE.67.016119

We examine numerically the storage capacity and the behaviour near saturation of an attractor neural network consisting of bistable elements with an adjustable coupling strength, the Bistable Gradient Network (BGN). For strong coupling, we find evidence of a first-order "memory blackout" phase transition as in the Hopfield network. For weak coupling, on the other hand, there is no evidence of such a transition and memorized patterns can be stable even at high levels of loading. The enhanced storage capacity comes, however, at the cost of imperfect retrieval of the patterns from corrupted versions.

Affiliated with

Also associated with

No associations

Rating

Bistable Gradient Networks II: Storage Capacity and Behaviour Near Saturation 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 II: Storage Capacity and Behaviour Near Saturation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Bistable Gradient Networks II: Storage Capacity and Behaviour Near Saturation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-454215