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 language | English |
---|---|
Title of host publication | Connectionist Models of Behavior and Cognition: Proceedings of the 11th Neural Computation and Psychology Workshop |
Subtitle of host publication | (Progress in Neural Processing) |
Editors | Mayor Julien, Nicholas Ruh, Kim Plunkett |
Publisher | World Scientific Publishing |
Pages | 103-113 |
Number of pages | 11 |
Volume | 18 |
ISBN (Electronic) | 978-981-283-422-5 |
ISBN (Print) | 981-283-422-2 |
DOIs | |
Publication status | Published - 2009 |
Event | Proceedings of the 11th Neural Computation and Psychology Worksho - Oxford, United Kingdom Duration: 16 Jul 2008 → 18 Jul 2008 |
Conference
Conference | Proceedings of the 11th Neural Computation and Psychology Worksho |
---|---|
Country/Territory | United Kingdom |
City | Oxford |
Period | 16/07/08 → 18/07/08 |