The synchronous BEG neural network with variable dilution

Details The synchronous BEG neural network with variable dilution The synchronous BEG neural network with variable dilution

2005-05-12

arxiv.org/abs/cond-mat/0505326v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

10 pages in Latex, 15 postscript figures

Scientific paper

The thermodynamic and retrieval properties of the Blume-Emery-Griffiths neural network with synchronous updating and variable dilution are studied using replica mean-field theory. Several forms of dilution are allowed by pruning the different types of couplings present in the Hamiltonian. The appearance and properties of two-cycles are discussed. Capacity-temperature phase diagrams are derived for several values of the pattern activity. The results are compared with those for sequential updating. The effect of self-coupling is studied. Furthermore, the optimal combination of dilution parameters giving the largest critical capacity is obtained.

Affiliated with

Also associated with

No associations

Rating

The synchronous BEG neural network with variable dilution 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 The synchronous BEG neural network with variable dilution, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The synchronous BEG neural network with variable dilution will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-162818