ROBUSTNESS TO NOISE OF ASSOCIATIVE MEMORY USING NONMONOTONIC ANALOG NEURONS

In this paper, dependence of storage capacity of an analogue associati ve memory model using nonmonotonic neurons on static synaptic noise an d static threshold noise is shown. This dependence is analytically cal culated by means of the self-consistent signal-to-noise analysis (SCSN A) proposed by Shiino and Fukai. It is known that the storage capacity of an associative memory model can be improved markedly by replacing the usual sigmoid neurons with nonmonotonic ones, and the Hopfield mod el has theoretically been shown to be fairly robust against introducin g the static synaptic noise. In this paper, it is shown that when the monotonicity of neuron is high, the storage capacity decreases rapidly according to an increase of the static synaptic noise. It is also sho wn that the reduction of the storage capacity is more sensitive to an increase in the static threshold noise than to the increase in the sta tic synaptic noise.