信息通信技术与政策2026，Vol.52Issue(1)：75-83,9.DOI:10.12267/j.issn.2096-5931.2026.01.010
克服人工神经网络灾难性遗忘的连续学习算法研究
Research on continual learning method for overcoming catastrophic forgetting of artificial neural networks
于达 1董晓飞 1曹峰 1查富生 2孙立宁2
作者信息
- 1. 中国信息通信研究院人工智能研究所,北京 100191||人工智能关键技术和应用评测工业和信息化部重点实验室,北京 100191
- 2. 哈尔滨工业大学机器人技术与系统全国重点实验室,哈尔滨 150000
- 折叠
摘要
Abstract
Traditional artificial neural network training typically focuses on closed,static,independent and identically distributed data,and performs a single task after completing offline training.However,when the data distribution continuously changes with the environment,the model will forget the knowledge learned from previous tasks,a phenomenon known as"catastrophic forgetting".As an emerging learning paradigm,continual learning aims to endow models with the ability to continuously learn,accumulate,and consolidate knowledge from data streams with constantly changing distributions.This enables artificial neural networks to achieve a"stability-plasticity"balance,thereby overcoming catastrophic forgetting.Through in-depth analysis of the key characteristics of current continual learning algorithms,a real-world robotic physical verification platform was established.The effectiveness of continual learning algorithms was verified in the scenario of robotic physical object grasping.Experimental results show that when the Contrastive Correlation Preserving Replay(CCPR)algorithm is applied to the robotic physical object grasping task,the average accuracy of the grasping task increases by 26.67％,better assisting the robot in performing the target task.关键词
人工智能/人工神经网络/连续学习/灾难性遗忘Key words
artificial intelligence/artificial neural networks/continual learning/catastrophic forgetting分类
信息技术与安全科学引用本文复制引用
于达,董晓飞,曹峰,查富生,孙立宁..克服人工神经网络灾难性遗忘的连续学习算法研究[J].信息通信技术与政策,2026,52(1):75-83,9.
