M. Okada et al., RANDOM AND SYSTEMATIC DILUTIONS OF SYNAPTIC CONNECTIONS IN A NEURAL-NETWORK WITH A NONMONOTONIC RESPONSE FUNCTION, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics, 57(2), 1998, pp. 2095-2103
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.