Connection strategy and performance in sparsely connected 2D associative memory models with non-random images

Abstract

A sparsely connected associative memory model is tested with different pattern sets, and it is found that pattern recall is highly dependent on the type of patterns used. Performance is also found to depend critically on the connection strategy used to build the networks. Comparisons of topology reveal that connectivity matrices based on Gaussian distributions perform well for all pattern types tested, and that for best pattern recall at low wiring costs, the optimal value of Gaussian used in creating the connection matrix is dependent on properties of the pattern set.