Statistical Temperature Coefficient Distribution in Analog RRAM Array: Impact on Neuromorphic System and Mitigation Method

TL;DR

This paper investigates the statistical distribution of temperature coefficient in analog RRAM devices, models its physical mechanisms, and proposes mitigation strategies to improve neuromorphic system accuracy.

Contribution

It introduces a compact model for Tα distribution in RRAM, elucidates its physical basis, and offers an optimization method to enhance neuromorphic computing accuracy.

Findings

Model accurately predicts Tα distribution across resistance states.

Proposed mitigation improves MNIST classification accuracy from 79.8% to 89.6%.

Thermal instability impacts conductance and system performance.

Abstract

Emerging analog resistive random access memory (RRAM) based on HfOx is an attractive device for non-von Neumann neuromorphic computing systems. The differences in temperature dependent conductance drift among cells hamper computing accuracy, characterized by the statistical distribution of temperature coefficient(T{\alpha}). A compact model was presented in order to investigate the statistical distribution of T{\alpha} under different resistance states. Based on this model, the physical mechanism of thermal instability of cells with a positive T{\alpha} was elucidated. Furthermore, this model can also effectively evaluate the impact of conductance distribution of different levels under various temperatures in artificial neural networks (ANN). An approach incorporating the optimized conductance range selection and the current compensation scheme was proposed to reduce the impacts of the distribution of T{\alpha}. The simulation results showed that recognition accuracy was improved from 79.8% to 89.6% for the application of MNIST handwriting digits classification with a two-layer perceptron at 400K after adopting the proposed optimization method.