Interacting neural networks

R. Metzler, W. Kinzel, I. Kanter

Research output: Contribution to journalArticlepeer-review

63 Scopus citations

Abstract

Several scenarios of mutually interacting neural networks were studied. Using perceptrons with well-known on-line training algorithms in the limit of infinite system size, exact equations of motion were derived for the dynamics of order parameters that describe the properties of the system. The information given in this study open the road to a general understanding of interacting adaptive systems with possible applications in biology, computer science, and economics.

Original languageEnglish
Pages (from-to)2555-2565
Number of pages11
JournalPhysical Review E
Volume62
Issue number2 B
DOIs
StatePublished - Aug 2000

Fingerprint

Dive into the research topics of 'Interacting neural networks'. Together they form a unique fingerprint.

Cite this