The phase space of interactions in neural networks with definite symmetry

E. Gardner, H. Gutfreund, I. Yekutieli

Research output: Contribution to journalArticlepeer-review

33 Scopus citations

Abstract

We calculate the typical fraction of the phase space of interactions which solve the problemof storing a given set of p patterns represented as N-spin configurations, as a function of the storage ratio, a =p/N , of the stability parameter, K, and of the symmetry, 7, of the interaction matrices. The calculation is performed for strongly diluted networks, where the connectivityof each spin, C, is of the order of In N. For each value of K and 17, there is a maximal value of a, above which the volume of solutions vanishes. For each value of K and a, there is a typical value of 7at which this volume is maximal. The analytical studies are supplemented by numerical simulations on fully connected and diluted networks, using specific learning algorithms.

Original languageEnglish
Pages (from-to)1995-2008
Number of pages14
JournalJournal of Physics A: Mathematical and General
Volume22
Issue number12
DOIs
StatePublished - 21 Jun 1989

Fingerprint

Dive into the research topics of 'The phase space of interactions in neural networks with definite symmetry'. Together they form a unique fingerprint.

Cite this