Open AccessMixed‐Precision Continual Learning Based on Computational Resistance Random Access Memory
Author(s) -
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
Publication year - 2022
Publication title -
advanced intelligent systems
Language(s) - English
Resource type - Journals
ISSN - 2640-4567
DOI - 10.1002/aisy.202270036
Subject(s) - forgetting , neuromorphic engineering , computer science , artificial intelligence , artificial neural network , efficient energy use , machine learning , enhanced data rates for gsm evolution , engineering , psychology , cognitive psychology , electrical engineering
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.