Vector neural net identifying many strongly distorted and correlated patterns
Boris Kryzhanovsky, Andrei L. Mikaelian, A. Fonarev · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2005
We suggest an effective and simple algorithm providing a polynomial storage capacity of a network of the form M ~ N2s+1, where N is the dimension of the stored binary patterns. In this problem the value of the free parameter s is restricted by the inequalities N >> slnN ≥ 1. The algorithm allows us to identify a large number of highly distorted similar patterns. The negative influence of correlations of the patterns is suppressed by choosing a sufficiently large value of the parameter s. We show the efficiency of the algorithm by the example of a perceptron identifier, but it also can be used to increase the storage capacity of full connected systems of associative memory.