High Performance Associative Memories and Structured Weight Dilution
View/ Open
Author
Turvey, S.P.
Hunt, S.
Davey, N.
Frank, R.
Attention
2299/3973
Abstract
The consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental investigations into the effect of dilution on factors such as: pattern stability and attractor performance. It is concluded that these networks maintain a reasonable level of performance at fairly high dilution rates.