The Capacity and Attractor Basins of Associative Memory Models

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.

• Type: Conference
• Year: 1999
• Where: IWANN
• Authors: Neil Davey, S. P. Hunt
• Keywords: IWANN 1999, Neural Networks, Performance Metrics, Significant Negative Effect, Significant Performance Gains