Synergistic Development of Perovskite Memristors and Algorithms for Robust Analog Computing

TL;DR

This paper presents a combined approach to optimize perovskite memristor fabrication and develop robust analog neural networks, enabling energy-efficient deep learning with improved performance and resilience to device imperfections.

Contribution

It introduces a synergistic methodology using Bayesian optimization for memristor fabrication and a novel training strategy for DNNs to handle memristor non-idealities, advancing analog computing.

Findings

Achieved up to 100-fold performance improvements in diverse tasks.

Validated high accuracy and low energy consumption on a 10x10 memristor crossbar.

Enabled deeper and wider networks for analog computing.

Abstract

Analog computing using non-volatile memristors has emerged as a promising solution for energy-efficient deep learning. New materials, like perovskites-based memristors are recently attractive due to their cost-effectiveness, energy efficiency and flexibility. Yet, challenges in material diversity and immature fabrications require extensive experimentation for device development. Moreover, significant non-idealities in these memristors often impede them for computing. Here, we propose a synergistic methodology to concurrently optimize perovskite memristor fabrication and develop robust analog DNNs that effectively address the inherent non-idealities of these memristors. Employing Bayesian optimization (BO) with a focus on usability, we efficiently identify optimal materials and fabrication conditions for perovskite memristors. Meanwhile, we developed "BayesMulti", a DNN training strategy utilizing BO-guided noise injection to improve the resistance of analog DNNs to memristor imperfections. Our approach theoretically ensures that within a certain range of parameter perturbations due to memristor non-idealities, the prediction outcomes remain consistent. Our integrated approach enables use of analog computing in much deeper and wider networks, which significantly outperforms existing methods in diverse tasks like image classification, autonomous driving, species identification, and large vision-language models, achieving up to 100-fold improvements. We further validate our methodology on a 10$\times$10 optimized perovskite memristor crossbar, demonstrating high accuracy in a classification task and low energy consumption. This study offers a versatile solution for efficient optimization of various analog computing systems, encompassing both devices and algorithms.