We consider two models of Hopfield-like associative memory with $q$-valuedneurons: Potts-glass neural network (PGNN) and parametrical neural network(PNN). In these models neurons can be in more than two different states. Themodels have the record characteristics of its storage capacity and noiseimmunity, and significantly exceed the Hopfield model. We present a uniformformalism allowing us to describe both PNN and PGNN. This networks inherentmechanisms, responsible for outstanding recognizing properties, are clarified.
展开▼