Memristor Crossbar Scaling Limits and the Implementation of a Large Neural Network Using 3D Stacked Crossbars

Memristor crossbar-based neural networks perform parallel operations in the analog domain. Ex-situ training approach needs to program the predetermined resistance values to the memristor crossbar. Because of the stochasticity of the memristor devices, programming a memristor needs to read the device resistance value iteratively. Reading a single memristor in a crossbar (without an isolation transistor) is challenging due to the sneak path current. Programming a memristor in a crossbar to either the R ON or R OFF state is relatively straight-forward. A neural network implemented using higher precision weights provides higher classification accuracy compared to a Ternary Neural Network (TNN). This paper demonstrates an implementation of memristor-based neural networks using only the two resistance values ( R ON , R OFF ). We have examined the impact of the device R ON / R OFF ratio, driver size on the scaling of the memristor-based neural network circuit. We have implemented a large neural network using multiple smaller 3D stacked crossbar arrays. We also have proposed novel neuron circuits to achieve higher weight precision. Our experimental result shows that the proposed higher precision synapses are easy to program and provide better classification accuracy compared to a TNN.