A Discrete-State Spiking Neuron Model and its Learning Potential By

In this paper we review some of our recent results on discrete-state spiking neuron models. The discrete-state spiking neuron model is a wired system of shift registers and can generate various spike-trains by adjusting the pattern of the wirings. In this paper we show basic relations between the wiring pattern and characteristics of the spike-train. We also show a learning algorithm which utilizes successive changes of the wiring pattern. It is shown that the learning algorithm enables the neuron to approximate various spike-trains generated by a chaotic analog spiking neuron