Spike Attention Coding for Spiking Neural Networks

doi:10.1109/TNNLS.2023.3310263

CASIA OpenIR > 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, Guoqi2 ; Pei, Jing 1; Deng, Lei 1,3
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
	2023-09-11
页码	7
通讯作者	Deng, Lei(leideng@mail.tsinghua.edu.cn)
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.
关键词	Rate coding spike attention coding (SAC) spiking neural networks (SNNs) temporal coding
DOI	10.1109/TNNLS.2023.3310263
关键词[WOS]	REPRESENTATION
收录类别	SCI
语种	英语
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]
项目资助者	Science and Technology Innovation 2030-New Generation of Artificial Intelligence,China Project ; National Natural Science Foundation of China ; Chinese Institute for Brain Research, Beijing
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:001068981500001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53123
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.