A Solid-State Electronic Linear Adaptive Neuron With Electrically Reprogrammabe Synapses

This paper addresses the implementation of a semiconductor device used to siniulate the synaptic interconnection in hardware realization of neural network systems. We have incorporated these modifiable synaptic weights into a solid-state electronic linear adaptive neuron with a Widrow-Hoff's delta learning rule as the updating algorithm to investigate the electrical performance of these programmable synapses. The experimental and simulation results are also presented in the paper.