Dynamics of interacting neural networks

W. Kinzel, R. Metzler, I. Kanter

Research output: Contribution to journalArticlepeer-review

29 Scopus citations

Abstract

The dynamics of interacting perceptrons is solved analytically. For a directed flow of information the system runs into a state which has a higher symmetry than the topology of the model. A symmetry-breaking phase transition is found with increasing learning rate. In addition, it is shown that a system of interacting perceptrons which is trained on the history of its minority decisions develops a good strategy for the problem of adaptive competition known as the bar problem or minority game.

Original languageEnglish
Pages (from-to)L141-L147
JournalJournal of Physics A: Mathematical and General
Volume33
Issue number14
DOIs
StatePublished - 14 Apr 2000

Fingerprint

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

Cite this