Gaussian and Exponential Architectures in Small-World Associative Memories

L. Calcraft, R.G. Adams, N. Davey

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

6 Citations (Scopus)
32 Downloads (Pure)

Abstract

The performance of sparsely-connected associative memory models built from a set of perceptrons is investigated using different patterns of connectivity. Architectures based on Gaussian and exponential distributions are compared to networks created by progressively rewiring a locally-connected network. It is found that while all three architectures are capable of good pattern-completion performance, the Gaussian and exponential architectures require a significantly lower mean wiring length to achieve the same results. In the case of networks of low connectivity, relatively tight Gaussian and exponential distributions achieve the best overall performance.
Original languageEnglish
Title of host publicationProcs of the European Symposium on Artificial Neural Networks, ESANN'06
Pages617-622
Publication statusPublished - 2006
Event2006 European Symposium on Artificial Neural Networks, ESANN '06 - Bruges, Belgium
Duration: 26 Apr 200628 Apr 2006

Conference

Conference2006 European Symposium on Artificial Neural Networks, ESANN '06
Country/TerritoryBelgium
CityBruges
Period26/04/0628/04/06

Fingerprint

Dive into the research topics of 'Gaussian and Exponential Architectures in Small-World Associative Memories'. Together they form a unique fingerprint.

Cite this