Adaptive weighted outer-product learning associative memory

Associative-memory neural networks with adaptive weighted outer-product learning are proposed in this paper. For the correct recall of a fundamental memory (FM), a corresponding learning weight is attached and a parameter called signal-to-noise-ratio-gain (SNRG) is devised. The sufficient conditions for the learning weights and the SNRG´s are derived. It is found both empirically and theoretically that the SNRG´s have their own threshold values for correct recalls of the corresponding FM´s. Based on the gradient-descent approach, several algorithms are constructed to adaptively find the optimal learning weights with reference to global- or local-error measure