Phase transitions in dilute, locally connected neural networks

Katherine J. Strandburg*, Michael A. Peshkin, Daniel F. Boyd, Christopher Chambers, Brennan Oe Keefe

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

We report numerical studies of the memory-loss phase transition in Hopfield-like symmetric neural networks in which the neurons are connected to all other neurons within a local neighborhood (dense, short-range connectivity). The number of connections per neuron K scales as the number of neurons N raised to a power less than 1 (i.e., KN, <1). We use the recently developed Lee-Kosterlitz finite-size scaling technique to determine the critical value of below which the first-order phase transition disappears.

Original languageEnglish (US)
Pages (from-to)6135-6138
Number of pages4
JournalPhysical Review A
Volume45
Issue number8
DOIs
StatePublished - 1992

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Fingerprint Dive into the research topics of 'Phase transitions in dilute, locally connected neural networks'. Together they form a unique fingerprint.

Cite this