Spike Attention Coding for Spiking Neural Networks

doi:10.1109/TNNLS.2023.3310263

CORC > 自动化研究所 > 中国科学院自动化研究所 > 脑图谱与类脑智能实验室

	Spike Attention Coding for Spiking Neural Networks
	Liu, Jiawen 1; Hu, Yifan 1; Li, Guoqi 2; Pei, Jing 1; Deng, Lei 1,3
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2023-09-11
页码	7
关键词	Rate coding spike attention coding (SAC) spiking neural networks (SNNs) temporal coding
ISSN号	2162-237X
DOI	10.1109/TNNLS.2023.3310263
通讯作者	Deng, Lei(leideng@mail.tsinghua.edu.cn)
英文摘要	Spiking neural networks (SNNs), an important family of neuroscience-oriented intelligent models, play an essential role in the neuromorphic computing community. Spike rate coding and temporal coding are the mainstream coding schemes in the current modeling of SNNs. However, rate coding usually suffers from limited representation resolution and long latency, while temporal coding usually suffers from under-utilization of spike activities. To this end, we propose spike attention coding (SAC) for SNNs. By introducing learnable attention coefficients for each time step, our coding scheme can naturally unify rate coding and temporal coding, and then flexibly learn optimal coefficients for better performance. Several normalization and regularization techniques are further incorporated to control the range and distribution of the learned attention coefficients. Extensive experiments on classification, generation, and regression tasks are conducted and demonstrate the superiority of the proposed coding scheme. This work provides a flexible coding scheme to enhance the representation power of SNNs and extends their application scope beyond the mainstream classification scenario.
资助项目	Science and Technology Innovation 2030-New Generation of Artificial Intelligence,China Project ; National Natural Science Foundation of China[2020AAA0109100] ; National Natural Science Foundation of China[62106119] ; Chinese Institute for Brain Research, Beijing ; [62276151]
WOS关键词	REPRESENTATION
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001068981500001
资助机构	Science and Technology Innovation 2030-New Generation of Artificial Intelligence,China Project ; National Natural Science Foundation of China ; Chinese Institute for Brain Research, Beijing
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53122]
专题	脑图谱与类脑智能实验室
通讯作者	Deng, Lei
作者单位	1.Tsinghua Univ, Ctr Brain Inspired Comp Res, Dept Precis Instrument, Beijing 100084, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100098, Peoples R China 3.Chinese Inst Brain Res, Beijing 102206, Peoples R China
推荐引用方式 GB/T 7714	Liu, Jiawen,Hu, Yifan,Li, Guoqi,et al. Spike Attention Coding for Spiking Neural Networks[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:7.
APA	Liu, Jiawen,Hu, Yifan,Li, Guoqi,Pei, Jing,&Deng, Lei.(2023).Spike Attention Coding for Spiking Neural Networks.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,7.
MLA	Liu, Jiawen,et al."Spike Attention Coding for Spiking Neural Networks".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):7.