Replica Symmetry Breaking in Attractor Neural Network Models

Details Replica Symmetry Breaking in Attractor Neural Network Models Replica Symmetry Breaking in Attractor Neural Network Models

1994-04-13

arxiv.org/abs/cond-mat/9404036v1

Physics

Condensed Matter

Latex file, 20 pages, 8 Figures available from the authors upon request, HD-TVP-94-4

Scientific paper

10.1007/BF01312198

The phenomenon of replica symmetry breaking is investigated for the retrieval phases of Hopfield-type network models. The basic calculation is done for the generalized version of the standard model introduced by Horner [1] and by Perez-Vicente and Amit [2] which can exhibit low mean levels of neural activity. For a mean activity $\bar a =1/2$ the Hopfield model is recovered. In this case, surprisingly enough, we cannot confirm the well known one step replica symmetry breaking (1RSB) result for the storage capacity which was presented by Crisanti, Amit and Gutfreund [3] ($\alpha_c^{\hbox{\mf 1RSB}}\simeq 0.144$). Rather, we find that 1RSB- and 2RSB-Ans\"atze yield only slightly increased capacities as compared to the replica symmetric value ($\alpha_c^{\hbox{\mf 1RSB}}\simeq 0.138\,186$ and $\alpha_c^{\hbox{\mf 2RSB}}\simeq 0.138\,187 $ compared to $\alpha_c^{\hbox{\mf RS}}\simeq 0.137\,905$), significantly smaller also than the value $\alpha_c^{\hbox{\mf sim}} = 0.145\pm 0.009$ reported from simulation studies. These values still lie within the recently discovered reentrant phase [4]. We conjecture that in the infinite Parisi-scheme the reentrant behaviour disappears as is the case in the SK-spin-glass model (Parisi--Toulouse-hypothesis). The same qualitative results are obtained in the low activity range.

Affiliated with

Also associated with

No associations

Rating

Replica Symmetry Breaking in Attractor Neural Network Models 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 Replica Symmetry Breaking in Attractor Neural Network Models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Replica Symmetry Breaking in Attractor Neural Network Models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-441186