Memristor Crossbar-Based Neuromorphic Computing System: A Case Study

TLDR

Neuromorphic hardware mimics biological systems but is limited by Von Neumann architecture; recent work uses memristors, which resemble synapses, to enhance scalability and performance. The study investigates a memristor crossbar array as an autoassociative memory applied to brain‑state‑in‑a‑box neural networks. The authors implement recall and training for a multi‑answer character recognition BSB model on the crossbar and evaluate its robustness through extensive Monte Carlo simulations accounting for input defects, process variations, and electrical fluctuations. The results show that the hardware‑based training scheme proposed in the paper can alleviate and even cancel out the majority of the noise issue.

Abstract

By mimicking the highly parallel biological systems, neuromorphic hardware provides the capability of information processing within a compact and energy-efficient platform. However, traditional Von Neumann architecture and the limited signal connections have severely constrained the scalability and performance of such hardware implementations. Recently, many research efforts have been investigated in utilizing the latest discovered memristors in neuromorphic systems due to the similarity of memristors to biological synapses. In this paper, we explore the potential of a memristor crossbar array that functions as an autoassociative memory and apply it to brain-state-in-a-box (BSB) neural networks. Especially, the recall and training functions of a multianswer character recognition process based on the BSB model are studied. The robustness of the BSB circuit is analyzed and evaluated based on extensive Monte Carlo simulations, considering input defects, process variations, and electrical fluctuations. The results show that the hardware-based training scheme proposed in the paper can alleviate and even cancel out the majority of the noise issue.