论文部分内容阅读
A double-patr associative memory neural network with patt loop is proposed. It can store 2N bit bipolar binary Patts up to the order of 22N, retrieve part or all of the stored patrems which all have the minimum Hamming distance with input Patt, completely eliminate spurious Patts, and has higher storing efficiency and reliability than conventional associative memory. The length of a Patt stored in this associative memory can be easily extended from 2N to kN.