Binary-Weighted Synaptic Circuit for Neuromorphic Learning System Using Stochastic Memristor SPICE Model

Abstract

The memristive device is a nanoscale nonlinear passive two-terminal fourth fundamental circuit element in addition to the three previously known passive fundamental circuit elements namely resistor, capacitor, and inductor. However aside from its non-volatile memory nature, this memristor resistance/ memristance controlled in the circuit operation by the amount of charge applied between its terminals. The memristor device SPICE modeling is significant for memristive circuit and neuromorphic system design. Nowadays probabilistic switching behavior observed in many fabricated memristor devices that inspired stochastic learning rule for memristor-based neuromorphic learning system application. In this paper, a stochastic metastable switch memristor model (MSSs) is used for binary-weighted memristor-based artificial synapse circuitry presentation. Using this MSSs memristor SPICE model a binary-weighted memristor-based artificial synapse circuit presented. The presented circuit shows a binary response to the signal given to the memristor implemented in the binary synaptic circuit using a stochastic memristor device model. The authors left the implementation of the proposed binary synaptic circuit in a memristor-based artificial neural network that functions through the clipped perceptron (CP) learning algorithm as future work.