Current-mode Memristor Crossbars for Neuromemristive Systems

TL;DR

This paper investigates current-mode memristor crossbars for neuromemristive systems, showing they can replicate voltage-mode weights with proper bounds and enabling backpropagation training, with similar accuracy demonstrated in simulations.

Contribution

It introduces a method to map voltage-mode weights to current-mode crossbars and derives a gradient descent rule for current-mode training, expanding design options for neuromemristive systems.

Findings

Current-mode and voltage-mode designs achieve similar accuracy on MNIST.

Current-mode weights can be derived from voltage-mode weights with bounds.

Both designs exhibit comparable defect tolerance.

Abstract

Motivated by advantages of current-mode design, this brief contribution explores the implementation of weight matrices in neuromemristive systems via current-mode memristor crossbar circuits. After deriving theoretical results for the range and distribution of weights in the current-mode design, it is shown that any weight matrix based on voltage-mode crossbars can be mapped to a current-mode crossbar if the voltage-mode weights are carefully bounded. Then, a modified gradient descent rule is derived for the current-mode design that can be used to perform backpropagation training. Behavioral simulations on the MNIST dataset indicate that both voltage and current-mode designs are able to achieve similar accuracy and have similar defect tolerance. However, analysis of trained weight distributions reveals that current-mode and voltage-mode designs may use different feature representations.