The capacity and attractor basins of associative memory models

N. Davey, S. Hunt

    Research output: Contribution to journalArticlepeer-review

    4 Citations (Scopus)
    54 Downloads (Pure)

    Abstract

    The performance characteristics of five variants of the Hopfield network are examined. Two performance metrics are used: memory capacity, and a measure of the size of basins of attraction. We find that the posttraining adjustment of processor thresholds has, at best, little or no effect on performance, and at worst a significant negative effect. The adoption of a local learning rule can, however, give rise to significant performance gains.
    Original languageEnglish
    Pages (from-to)330-339
    JournalLecture Notes in Computer Science (LNCS)
    Volume1606
    DOIs
    Publication statusPublished - 1999

    Fingerprint

    Dive into the research topics of 'The capacity and attractor basins of associative memory models'. Together they form a unique fingerprint.

    Cite this