CASIA OpenIR  > 复杂系统认知与决策实验室
Attention Spiking Neural Networks
Yao, Man1,2; Zhao, Guangshe1; Zhang, Hengyu3; Hu, Yifan4; Deng, Lei4; Tian, Yonghong2,5; Xu, Bo6; Li, Guoqi6
Source PublicationIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN0162-8828
2023-08-01
Volume45Issue:8Pages:9393-9410
Corresponding AuthorLi, Guoqi(guoqi.li@ia.ac.cn)
AbstractBrain-inspired spiking neural networks (SNNs) are becoming a promising energy-efficient alternative to traditional artificial neural networks (ANNs). However, the performance gap between SNNs and ANNs has been a significant hindrance to deploying SNNs ubiquitously. To leverage the full potential of SNNs, in this paper we study the attention mechanisms, which can help human focus on important information. We present our idea of attention in SNNs with a multi-dimensional attention module, which infers attention weights along the temporal, channel, as well as spatial dimension separately or simultaneously. Based on the existing neuroscience theories, we exploit the attention weights to optimize membrane potentials, which in turn regulate the spiking response. Extensive experimental results on event-based action recognition and image classification datasets demonstrate that attention facilitates vanilla SNNs to achieve sparser spiking firing, better performance, and energy efficiency concurrently. In particular, we achieve top-1 accuracy of 75.92% and 77.08% on ImageNet-1 K with single/4-step Res-SNN-104, which are state-of-the-art results in SNNs. Comparedwith counterpart Res-ANN-104, the performance gap becomes -0.95/+0.21 percent and the energy efficiency is 31.8x/7.4x. To analyze the effectiveness of attention SNNs, we theoretically prove that the spiking degradation or the gradient vanishing, which usually holds in general SNNs, can be resolved by introducing the block dynamical isometry theory. We also analyze the efficiency of attention SNNs based on our proposed spiking response visualization method. Our work lights up SNN's potential as a general backbone to support various applications in the field of SNNresearch, with a great balance between effectiveness and energy efficiency.
KeywordAttention mechanism efficient neuromorphic inference neuromorphic computing spiking neural network
DOI10.1109/TPAMI.2023.3241201
WOS KeywordCLASSIFICATION ; COMMUNICATION ; INTELLIGENCE ; MECHANISMS
Indexed BySCI
Language英语
Funding ProjectBeijing Natural Science Foundation for Distinguished Young Scholars[JQ21015] ; National Key R&D Program of China[2018AAA0102600] ; National Natural Science Foundation of China[62236009] ; National Natural Science Foundation of China[61836004] ; National Natural Science Foundation of China[U22A20103]
Funding OrganizationBeijing Natural Science Foundation for Distinguished Young Scholars ; National Key R&D Program of China ; National Natural Science Foundation of China
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:001022958600008
PublisherIEEE COMPUTER SOC
Citation statistics
Cited Times:23[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/53886
Collection复杂系统认知与决策实验室
脑图谱与类脑智能实验室
Corresponding AuthorLi, Guoqi
Affiliation1.Xi An Jiao Tong Univ, Sch Automat Sci & Engn, Xian 710049, Shaanxi, Peoples R China
2.Peng Cheng Lab, Shenzhen 518066, Guangdong, Peoples R China
3.Tsinghua Univ, Tsinghua Shenzhen Int Grad Sch, Shenzhen 518071, Guangdong, Peoples R China
4.Tsinghua Univ, Dept Precis Instrument, Ctr Brain Inspired Comp Res, Beijing 100190, Peoples R China
5.Peking Univ, Inst Artificial Intelligence, Beijing 100871, Peoples R China
6.Chinese Acad Sci, Inst Automat, Beijing 100045, Peoples R China
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Yao, Man,Zhao, Guangshe,Zhang, Hengyu,et al. Attention Spiking Neural Networks[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(8):9393-9410.
APA Yao, Man.,Zhao, Guangshe.,Zhang, Hengyu.,Hu, Yifan.,Deng, Lei.,...&Li, Guoqi.(2023).Attention Spiking Neural Networks.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(8),9393-9410.
MLA Yao, Man,et al."Attention Spiking Neural Networks".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.8(2023):9393-9410.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yao, Man]'s Articles
[Zhao, Guangshe]'s Articles
[Zhang, Hengyu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yao, Man]'s Articles
[Zhao, Guangshe]'s Articles
[Zhang, Hengyu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yao, Man]'s Articles
[Zhao, Guangshe]'s Articles
[Zhang, Hengyu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.