中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 复杂系统认知与决策实验室
A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost

文献类型：期刊论文

作者Zhang, Tielin1,2,3; Cheng, Xiang1,3; Jia, Shuncheng1,3; Li, Chengyu T.2,4; Poo, Mu-ming2,4; Xu, Bo1,3
刊名SCIENCE ADVANCES
出版日期2023-08-01
卷号9期号:34页码:12
ISSN号2375-2548
DOI10.1126/sciadv.adi2947
通讯作者Zhang, Tielin(tielin.zhang@ia.ac.cn) ; Xu, Bo(xubo@ia.ac.cn)
英文摘要Neuromodulators in the brain act globally at many forms of synaptic plasticity, represented as metaplasticity, which is rarely considered by existing spiking (SNNs) and nonspiking artificial neural networks (ANNs). Here, we report an efficient brain-inspired computing algorithm for SNNs and ANNs, referred to here as neuromodulation-assisted credit assignment (NACA), which uses expectation signals to induce defined levels of neuromodulators to selective synapses, whereby the long-term synaptic potentiation and depression are modified in a nonlinear manner depending on the neuromodulator level. The NACA algorithm achieved high recognition accuracy with substantially reduced computational cost in learning spatial and temporal classification tasks. Notably, NACA was also verified as efficient for learning five different class continuous learning tasks with varying degrees of complexity, exhibiting a markedly mitigated catastrophic forgetting at low computational cost. Mapping synaptic weight changes showed that these benefits could be explained by the sparse and targeted synaptic modifications attributed to expectation-based global neuromodulation.
WOS关键词TIMING-DEPENDENT PLASTICITY ; DOPAMINE ; STDP ; SENSITIVITY ; MODULATION ; RECEPTORS
资助项目Strategic Priority Research Program of Chinese Academy of Sciences[XDA27010404] ; Shanghai Municipal Science and Technology Major Project[2021SHZDZX] ; Lingang Laboratory Fund[LG202105-01-07] ; Youth Innovation Promotion Association of CAS
WOS研究方向Science & Technology - Other Topics
语种英语
出版者AMER ASSOC ADVANCEMENT SCIENCE
WOS记录号WOS:001054596800013
资助机构Strategic Priority Research Program of Chinese Academy of Sciences ; Shanghai Municipal Science and Technology Major Project ; Lingang Laboratory Fund ; Youth Innovation Promotion Association of CAS
源URL[http://ir.ia.ac.cn/handle/173211/54161]  
专题复杂系统认知与决策实验室
通讯作者Zhang, Tielin; Xu, Bo
作者单位1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
2.Shanghai Ctr Brain Sci & Brain inspired Technol, Lingang Lab, Shanghai 200031, Peoples R China
3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Inst Neurosci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Tielin,Cheng, Xiang,Jia, Shuncheng,et al. A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost[J]. SCIENCE ADVANCES,2023,9(34):12.
APA Zhang, Tielin,Cheng, Xiang,Jia, Shuncheng,Li, Chengyu T.,Poo, Mu-ming,&Xu, Bo.(2023).A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost.SCIENCE ADVANCES,9(34),12.
MLA Zhang, Tielin,et al."A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost".SCIENCE ADVANCES 9.34(2023):12.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。