An auto-correlation associative memory which stores plural pattern vectors as its minimum states

A noise tolerant auto-correlation associative memory is proposed. An associated energy function is formed by a multiplication of plural Hopfield energy functions each of which includes a single pattern as its energy minimum. An asynchronous optimizing algorithm of the whole energy function is also presented based on the binary neuron model. The advantages of this new associative memory are that the orthogonality relation among patterns does not need to be satisfied and each stored pattern has a large basin around itself. The numerical simulations show a fairly good performance of associative memory for arbitrary pattern vectors which are not orthogonal to each other.