University of Hertfordshire

High Performance Associative Memories and Structured Weight Dilution

Research output: Chapter in Book/Report/Conference proceedingChapter

Documents

  • S.P. Turvey
  • S. Hunt
  • N. Davey
  • R. Frank
View graph of relations
Original languageEnglish
Title of host publicationApplications and Science in Soft Computing - Advances in Intelligent and Soft Computing , Vol. 24
EditorsA. Lotfi, J.M. Garibaldi
PublisherSpringer
Pages23-30
ISBN (Print)978-3-540-40856-7
Publication statusPublished - 2004

Abstract

The consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental investigations into the effect of dilution on factors such as: pattern stability and attractor performance. It is concluded that these networks maintain a reasonable level of performance at fairly high dilution rates.

Notes

Copyright Springer

ID: 85959