Asymmetric neural networks with multispin interactions

Research output: Contribution to journalArticlepeer-review

Abstract

A dilute nonsymmetric ferromagnetic neural network with multispin interactions and a version of the Hopfield model with multispin interactions are solved in the limit where the average number of inputs per spin is finite. It is found that in such asymmetric systems the critical exponents of local quantities can take a few different values, instead of just one.
Original languageAmerican English
JournalPhysical Review A (Atomic, Molecular and Optical Physics)
Volume38
Issue number11
StatePublished - 1988

Fingerprint

Dive into the research topics of 'Asymmetric neural networks with multispin interactions'. Together they form a unique fingerprint.

Cite this