Generalized Associative Memory Models for Data Fusion

Abstract

The Hopfield and bi-directional associative memory (BAM) models are well developed and carefully studied models for associative memory that are patterned after the memory structure of the animal brain. Their basic limitation is that they can only perform associations between at most two sets of patterns. Several different models for generalized associative memory are proposed here. These models are all extensions of the Hopfield and BAM models that can perform multiple associations. Extensive software simulations are conducted to evaluate the different models, using the memory capacity as basis for comparing their performance. The use of the Widrow-Hoff gradient descent error correction algorithm is introduced that can improve the memory capacities of the various models. Potential application of these models as data fusion systems is explored.