Neural networks with high order connections

Details Neural networks with high order connections Neural networks with high order connections

1993-06-17

arxiv.org/abs/cond-mat/9306039v1

Phys. Rev. E 47 (1993) 4060

Physics

Condensed Matter

24 pages, latex + 14 figures upon request, IFUFRGS-JJA-02-93

Scientific paper

10.1103/PhysRevE.48.4060

We present results for two different kinds of high order connections between neurons acting as corrections to the Hopfield model. Equilibrium properties are analyzed using the replica mean-field theory and compared with numerical simulations. An optimal learning algorithm for fourth order connections is given that improves the storage capacity without increasing the weight of the higher order term. While the behavior of one of the models qualitatively resembles the original Hopfield one, the other presents a new and very rich behavior: depending on the strength of the fourth order connections and the temperature, the system presents two distinct retrieval regions separated by a gap, as well as several phase transitions. Also, the spin glass states seems to disappear above a certain value of the load parameter $\alpha$, $\alpha_g$.

Affiliated with

Also associated with

No associations

Rating

Neural networks with high order connections 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 Neural networks with high order connections, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural networks with high order connections will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-397622