High performance associative memory models and weight dilution

N. Davey, R.G. Adams, S. Hunt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

35 Downloads (Pure)


The consequences of diluting the weights of the standard Hopfield architecture associative memory model, trained using perceptron like learning rules, is examined. A proportion of the weights of the network are removed; this can be done in a symmetric and asymmetric way and both methods are investigated. This paper reports experimental investigations into the consequences of dilution in terms of: capacity, training times and size of basins of attraction. It is concluded that these networks maintain a reasonable performance at fairly high dilution rates.
Original languageEnglish
Title of host publicationProcs of Int Conf on Neural Information Processing
Subtitle of host publicationICONIP'01
Publication statusPublished - 2001


Dive into the research topics of 'High performance associative memory models and weight dilution'. Together they form a unique fingerprint.

Cite this