Exploiting nonlinear dendritic adaptive computation in training deep Spiking Neural Networks

doi:10.1016/j.neunet.2023.10.056

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

	Exploiting nonlinear dendritic adaptive computation in training deep Spiking Neural Networks
	Shen, Guobin 1,3; Zhao, Dongcheng 1; Zeng, Yi 1,2,3
刊名	NEURAL NETWORKS
	2024-02-01
卷号	170 页码:190-201
关键词	Dendritic Nonlinearity Dendritic Spatial Gating Module Dendritic Temporal Adjust Module Spiking Neural Networks
ISSN号	0893-6080
DOI	10.1016/j.neunet.2023.10.056
通讯作者	Zeng, Yi(yi.zeng@ia.ac.cn)
英文摘要	Inspired by the information transmission process in the brain, Spiking Neural Networks (SNNs) have gained considerable attention due to their event-driven nature. However, as the network structure grows complex, managing the spiking behavior within the network becomes challenging. Networks with excessively dense or sparse spikes fail to transmit sufficient information, inhibiting SNNs from exhibiting superior performance. Current SNNs linearly sum presynaptic information in postsynaptic neurons, overlooking the adaptive adjust-ment effect of dendrites on information processing. In this study, we introduce the Dendritic Spatial Gating Module (DSGM), which scales and translates the input, reducing the loss incurred when transforming the continuous membrane potential into discrete spikes. Simultaneously, by implementing the Dendritic Temporal Adjust Module (DTAM), dendrites assign different importance to inputs of different time steps, facilitating the establishment of the temporal dependency of spiking neurons and effectively integrating multi-step time information. The fusion of these two modules results in a more balanced spike representation within the network, significantly enhancing the neural network's performance. This approach has achieved state-of-the -art performance on static image datasets, including CIFAR10 and CIFAR100, as well as event datasets like DVS-CIFAR10, DVS-Gesture, and N-Caltech101. It also demonstrates competitive performance compared to the current state-of-the-art on the ImageNet dataset.
资助项目	National Key Research and Devel-opment Program[2020AAA0107800]
WOS关键词	NEURONS
WOS研究方向	Computer Science ; Neurosciences & Neurology
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:001121849100001
资助机构	National Key Research and Devel-opment Program
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/55036]
专题	脑图谱与类脑智能实验室
通讯作者	Zeng, Yi
作者单位	1.Chinese Acad Sci, Inst Automat, Brain Inspired Cognit Intelligence Lab, Beijing 100190, Peoples R China 2.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China 3.Univ Chinese Acad Sci, Sch Future Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Shen, Guobin,Zhao, Dongcheng,Zeng, Yi. Exploiting nonlinear dendritic adaptive computation in training deep Spiking Neural Networks[J]. NEURAL NETWORKS,2024,170:190-201.
APA	Shen, Guobin,Zhao, Dongcheng,&Zeng, Yi.(2024).Exploiting nonlinear dendritic adaptive computation in training deep Spiking Neural Networks.NEURAL NETWORKS,170,190-201.
MLA	Shen, Guobin,et al."Exploiting nonlinear dendritic adaptive computation in training deep Spiking Neural Networks".NEURAL NETWORKS 170(2024):190-201.