Statistical performance of outer-product associative memory models

Arthur F. Gmitro, Paul E. Keller, Gene R. Gindi

Research output: Contribution to journalArticle

4 Scopus citations

Abstract

A figure of merit, the probability a bit is correct after update, is used to evaluate the performance of randomly coded outer-product associative memory models. Networks with bipolar binary states and nonzero diagonal connections are shown to yield the best performance with respect to this figure of merit. A surprising result is that an all-positive network, one with binary states and positive connections, is superior to a standard Hopfield style network with binary states and bipolar connections. A prescription for the optimal threshold point for the all-positive network is given.

Original languageEnglish (US)
Pages (from-to)1940-1952
Number of pages13
JournalApplied optics
Volume28
Issue number10
DOIs
StatePublished - May 15 1989

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Engineering (miscellaneous)
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Statistical performance of outer-product associative memory models'. Together they form a unique fingerprint.

  • Cite this