Brainwashing random asymmetric "neural" networks

P. C. McGuire, G. C. Littlewort, J. Rafelski

Research output: Contribution to journalArticle

3 Scopus citations

Abstract

An algorithm for synaptic modification (plasticity) is described by which a recurrently connected network of neuron-like units can organize itself to produce a sequence of activation states that does not repeat itself for a very long time. During the self-organization stage, the connections between the units undergo non-Hebbian modifications, which tend to decorrelate the activity of the units, thereby lengthening the period of the cyclic modes inherent in the network. It is shown that the peridiodicity of the activity rises exponentially with the amount of exposure to this plasticity algorithm. Threshold is also a critical parameter in determining cycle lengths, as is the rate of decay of the fields that accumulate at silent units.

Original languageEnglish (US)
Pages (from-to)255-260
Number of pages6
JournalPhysics Letters A
Volume160
Issue number3
DOIs
StatePublished - Nov 18 1991

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Fingerprint Dive into the research topics of 'Brainwashing random asymmetric "neural" networks'. Together they form a unique fingerprint.

  • Cite this