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
Attention Spiking Neural Networks

文献类型：期刊论文

作者Yao, Man3,4; Zhao, Guangshe3; Zhang, Hengyu2; Hu, Yifan1; Deng, Lei1; Tian, Yonghong4,6; Xu, Bo5; Li, Guoqi5
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2023-08-01
卷号45期号:8页码:9393-9410
ISSN号0162-8828
关键词Attention mechanism efficient neuromorphic inference neuromorphic computing spiking neural network
DOI10.1109/TPAMI.2023.3241201
通讯作者Li, Guoqi(guoqi.li@ia.ac.cn)
英文摘要Brain-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.
WOS关键词CLASSIFICATION ; COMMUNICATION ; INTELLIGENCE ; MECHANISMS
资助项目Beijing 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]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE COMPUTER SOC
WOS记录号WOS:001022958600008
资助机构Beijing Natural Science Foundation for Distinguished Young Scholars ; National Key R&D Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/53885]  
专题复杂系统认知与决策实验室
脑图谱与类脑智能实验室
通讯作者Li, Guoqi
作者单位1.Tsinghua Univ, Dept Precis Instrument, Ctr Brain Inspired Comp Res, Beijing 100190, Peoples R China
2.Tsinghua Univ, Tsinghua Shenzhen Int Grad Sch, Shenzhen 518071, Guangdong, Peoples R China
3.Xi An Jiao Tong Univ, Sch Automat Sci & Engn, Xian 710049, Shaanxi, Peoples R China
4.Peng Cheng Lab, Shenzhen 518066, Guangdong, Peoples R China
5.Chinese Acad Sci, Inst Automat, Beijing 100045, Peoples R China
6.Peking Univ, Inst Artificial Intelligence, Beijing 100871, Peoples R China
推荐引用方式
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.

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。