Optimal connection strategies in one- and two-dimensional associative memory models

This study examines the performance of sparsely-connected associative memory models built using a number of different connection strategies, applied to oneand two-dimensional topologies. Efficient patterns of connectivity are identified which yield high performance at relatively low wiring costs in both topologies. It is found that two-dimensional models are more tolerant of variations in connection strategy than their one-dimensional counterparts; though networks built with both topologies become less so as their connection density is decreased. Keywords—Associative memory models, efficient connection strategies, sparse connectivity, comparing 1D and 2D topologies