The performance pf sparsley-connected 2D associative memory models with non-random images

L. Calcraft, Roderick Adams, N. Davey

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

Abstract

A sparsely connected associative memory model is built with small-world connectivity, and trained on both random, and real-world image sets. It is found that pattern recall using real-world images can vary significantly from that of random images, and that the relationship between network wiring strategy and performance changes dramatically when training sets consist of certain types of real-world image.

Original languageEnglish
Title of host publicationConnectionist Models of Behavior and Cognition: Proceedings of the 11th Neural Computation and Psychology Workshop
Subtitle of host publication(Progress in Neural Processing)
EditorsMayor Julien, Nicholas Ruh, Kim Plunkett
PublisherWorld Scientific Publishing
Pages103-113
Number of pages11
Volume18
ISBN (Electronic)978-981-283-422-5
ISBN (Print)981-283-422-2
DOIs
Publication statusPublished - 2009
EventProceedings of the 11th Neural Computation and Psychology Worksho - Oxford, United Kingdom
Duration: 16 Jul 200818 Jul 2008

Conference

ConferenceProceedings of the 11th Neural Computation and Psychology Worksho
Country/TerritoryUnited Kingdom
CityOxford
Period16/07/0818/07/08

Fingerprint

Dive into the research topics of 'The performance pf sparsley-connected 2D associative memory models with non-random images'. Together they form a unique fingerprint.

Cite this