Mixed‐Precision Continual Learning Based on Computational Resistance Random Access Memory. (18th August 2022)

• Record Type: Journal Article
• Authors: Li, Yi; Zhang, Woyu; Xu, Xiaoxin; He, Yifan; Dong, Danian; Jiang, Nanjia; Wang, Fei; Guo, Zeyu; Wang, Shaocong; Dou, Chunmeng; Liu, Yongpan; Wang, Zhongrui; Shang, Dashan
• Is Part Of: Advanced intelligent systems. Volume 4:Number 8(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-08-18
• Subjects: Artificial intelligence -- Periodicals; Robotics -- Periodicals; Control theory -- Periodicals; 006.3
• DOI: 10.1002/aisy.202270036
• Languages: English
• ISSNs: 2640-4567

Abstract

Abstract : Continual Learning Artificial neural networks suffer from catastrophic forgetting when meeting sequential tasks. In article number 2200026, Zhongrui Wang, Dashan Shang, and co‐workers propose a metaplasticity‐inspired mixed‐precision continual learning model to address this issue. By deploying it on a neuromorphic prototype system with the in‐memory computing paradigm, outperforming energy efficiency and high accuracy are demonstrated, paving a promising way for autonomous edge systems.