Attractors in fully asymmetric neural networks

Details Attractors in fully asymmetric neural networks Attractors in fully asymmetric neural networks

1997-08-28

arxiv.org/abs/cond-mat/9708215v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

23 pages, 6 figures, Latex, to appear on J. Phys. A

Scientific paper

10.1088/0305-4470/30/16/007

The statistical properties of the length of the cycles and of the weights of the attraction basins in fully asymmetric neural networks (i.e. with completely uncorrelated synapses) are computed in the framework of the annealed approximation which we previously introduced for the study of Kauffman networks. Our results show that this model behaves essentially as a Random Map possessing a reversal symmetry. Comparison with numerical results suggests that the approximation could become exact in the infinite size limit.

Affiliated with

Also associated with

No associations

Rating

Attractors in fully asymmetric neural networks 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 Attractors in fully asymmetric neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Attractors in fully asymmetric neural networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-93062