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
  5. 听觉模型与认知计算
Self-backpropagation of synaptic modifications elevates the efficiency of spiking and artificial neural networks

文献类型：期刊论文

作者Zhang, Tielin2,3; Cheng, Xiang2,3; Jia, Shuncheng2,3; Poo, Mu-Ming1,3,4,5; Zeng, Yi1,2,3; Xu, Bo1,2,3
刊名SCIENCE ADVANCES
出版日期2021-10-01
卷号7期号:43页码:11
ISSN号2375-2548
DOI10.1126/sciadv.abh0146
通讯作者Xu, Bo(xubo@ia.ac.cn)
英文摘要Many synaptic plasticity rules found in natural circuits have not been incorporated into artificial neural networks (ANNs). We showed that incorporating a nonlocal feature of synaptic plasticity found in natural neural networks, whereby synaptic modification at output synapses of a neuron backpropagates to its input synapses made by upstream neurons, markedly reduced the computational cost without affecting the accuracy of spiking neural networks (SNNs) and ANNs in supervised learning for three benchmark tasks. For SNNs, synaptic modification at output neurons generated by spike timing-dependent plasticity was allowed to self-propagate to limited upstream synapses. For ANNs, modified synaptic weights via conventional backpropagation algorithm at output neurons self-backpropagated to limited upstream synapses. Such self-propagating plasticity may produce coordinated synaptic modifications across neuronal layers that reduce computational cost.
WOS关键词LONG-TERM POTENTIATION ; PROPAGATION ; NEURONS ; MEMORY ; MODEL
资助项目National Key R&D Program of China[2020AAA0104305] ; National Natural Science Foundation of China[61806195] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA27010404] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32070000] ; Key Research Program of Frontier Sciences, Chinese Academy of Sciences[QYZDY-SSW-SMCO01] ; International Partnership Program of Chinese Academy of Sciences[153D31KYSB20170059] ; Shanghai Municipal Science and Technology Major Project[2018SHZDZX05] ; Shanghai Key Basic Research Project[18JC1410100]
WOS研究方向Science & Technology - Other Topics
语种英语
WOS记录号WOS:000711845800010
出版者AMER ASSOC ADVANCEMENT SCIENCE
资助机构National Key R&D Program of China ; National Natural Science Foundation of China ; Strategic Priority Research Program of the Chinese Academy of Sciences ; Key Research Program of Frontier Sciences, Chinese Academy of Sciences ; International Partnership Program of Chinese Academy of Sciences ; Shanghai Municipal Science and Technology Major Project ; Shanghai Key Basic Research Project
源URL[http://ir.ia.ac.cn/handle/173211/46359]  
专题数字内容技术与服务研究中心_听觉模型与认知计算
类脑智能研究中心_类脑认知计算
通讯作者Xu, Bo
作者单位1.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
2.Chinese Acad Sci, Res Ctr Brain Inspired Intelligence, Inst Automat, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
4.Shanghai Ctr Brain Sci & Brain Inspired Intellige, Shanghai 201210, Peoples R China
5.Chinese Acad Sci, Inst Neurosci, State Key Lab Neurosci, Shanghai 200031, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Tielin,Cheng, Xiang,Jia, Shuncheng,et al. Self-backpropagation of synaptic modifications elevates the efficiency of spiking and artificial neural networks[J]. SCIENCE ADVANCES,2021,7(43):11.
APA Zhang, Tielin,Cheng, Xiang,Jia, Shuncheng,Poo, Mu-Ming,Zeng, Yi,&Xu, Bo.(2021).Self-backpropagation of synaptic modifications elevates the efficiency of spiking and artificial neural networks.SCIENCE ADVANCES,7(43),11.
MLA Zhang, Tielin,et al."Self-backpropagation of synaptic modifications elevates the efficiency of spiking and artificial neural networks".SCIENCE ADVANCES 7.43(2021):11.

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。