RANDOM AND SYSTEMATIC DILUTIONS OF SYNAPTIC CONNECTIONS IN A NEURAL-NETWORK WITH A NONMONOTONIC RESPONSE FUNCTION

It has been observed that the dilution of synaptic connections in neur al networks has relevance to biology and applicability to engineering. From this viewpoint, the effects of synaptic dilution on the retrieva l performance of an associative memory model with a nonmonotonic respo nse function are investigated through the self-consistent signal-to-no ise analysis. Compared with a fully connected neural network, for whic h a nonmonotonic response function is known to achieve a large enhance ment of storage capacity and the occurrence of the superretrieval phas e leads to an errorless memory retrieval, the nonmonotonic neural netw ork with a random synaptic dilution undergoes a considerable decrease in storage capacity. It is shown, however, that by employing a systema tic dilution technique characterized by a nonlinear learning rule, in which larger connections are retained, it is possible to significantly reverse the undesirable rapid reduction in storage capacity. It is al so proved that the superretrieval phase is structurally unstable again st the dilution of synapses.