A Fault-Tolerant Framework for Stuck-at Fault Mitigation in Memristor-Based Ternary Neural Networks

Due to their small size, low power consumption, and non-volatility, memristors are promising candidates for weight storage in ternary neural networks (TNNs). However, the inherent limitations of memristor manufacturing processes often result in faults, with stuck-at faults (SAFs) being the most prevalent, which severely degrade the accuracy and overall performance of memristor-based TNNs in practical applications. To address this challenge, a novel fault-tolerant framework is proposed to mitigate the negative impacts of SAFs. First, we analyze the factors that contribute to programmed error rates in memristor-based TNNs. The framework incorporates transformations such as flipping, permutation, and integrating redundant rows, which significantly mitigate the negative impact of SAFs and improve network accuracy. Experimental results show that even with SAF rates as high as 50% in memristor crossbar arrays, the proposed framework can effectively improve the accuracy of TNNs to near-ideal levels.