A Design Methodology for Fault-Tolerant Neuromorphic Computing Using Bayesian Neural Network

• Published in: Micromachines (Basel) Vol. 14; no. 10; p. 1840
• Main Authors: Gao, Di, Xie, Xiaoru, Wei, Dongxu
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 27.09.2023; MDPI
• Subjects: Analysis; Arrays; Bayesian analysis; Bayesian neural network; Design; Design engineering; Expected values; Fault tolerance; memristor crossbar array; Memristors; Methods; Neural networks; Neuromorphic computing; process variation; Statistical inference; variational inference

Memristor crossbar arrays are a promising platform for neuromorphic computing. In practical scenarios, the synapse weights represented by the memristors for the underlying system are subject to process variations, in which the programmed weight when read out for inference is no longer deterministic...