Resolution of associative memory's perplexity using additional information and exceptional knowledge

Concerns the application of fuzzy associative memories to complex knowledge processing. The authors propose a method to resolve associative memories' perplexity, which is due to their poor storage capacity. The perplexity is defined by the fact that, after the recalling processing, several undesired nodes may have almost the same activation as the desired ones. Furthermore the authors apply the proposed method to the construction of a facial expression model and show its effect.