MULTIVALUED ASSOCIATIVE MEMORIES BASED ON RECURRENT NETWORKS

In this paper we propose a multivalued neural associative memory model based on a recurrent network structure. This new model adopts the same principle proposed in our previous work, the exponential correlation associative memories (ECAM). The model also has a very high storage capacity and strong error-correction capability. The major components of the new model include a weighted average process and some similarity-measure computation. As in ECAM, in order to enhance the differences among the weights and make the largest weights more overwhelming, the new model incorporates a nonlinear function in the calculation of weights. We also suggest several possible similarity measures suitable for this model. Simulation results of the performance of the new model with different measures show that, loaded with 500 64-component patterns, the model can sustain noise with power about one fifth to three fifths of the average signal power.