Self-Lateral Propagation Elevates Synaptic Modifications in Spiking Neural Networks for the Efficient Spatial and Temporal Classification

doi:10.1109/TNNLS.2023.3286458

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	Self-Lateral Propagation Elevates Synaptic Modifications in Spiking Neural Networks for the Efficient Spatial and Temporal Classification
	Zhang, Tielin 1,3; Wang, Qingyu 1,3; Xu, Bo 1,2,3
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2023-06-30
页码	13
关键词	Self-lateral propagation (SLP) spatial classifica-tion spiking neural network (SNN) synaptic plasticity temporal classification
ISSN号	2162-237X
DOI	10.1109/TNNLS.2023.3286458
通讯作者	Zhang, Tielin(tielin.zhang@ia.ac.cn) ; Xu, Bo(xubo@ia.ac.cn)
英文摘要	The brain's mystery for efficient and intelligent computation hides in the neuronal encoding, functional circuits, and plasticity principles in natural neural networks. However, many plasticity principles have not been fully incorporated into artificial or spiking neural networks (SNNs). Here, we report that incorporating a novel feature of synaptic plasticity found in natural networks, whereby synaptic modifications self-propagate to nearby synapses, named self-lateral propagation (SLP), could further improve the accuracy of SNNs in three benchmark spatial and temporal classification tasks. The SLP contains lateral pre (SLPpre) and lateral post (SLPpost) synaptic propagation, describing the spread of synaptic modifications among output synapses made by axon collaterals or among converging synapses on the postsynaptic neuron, respectively. The SLP is biologically plausible and can lead to a coordinated synaptic modification within layers that endow higher efficiency without losing much accuracy. Furthermore, the experimental results showed the impressive role of SLP in sharpening the normal distribution of synaptic weights and broadening the more uniform distribution of misclassified samples, which are both considered essential for understanding the learning convergence and network generalization of neural networks.
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences (CAS)[XDB32070100] ; Strategic Priority Research Program of the Chinese Academy of Sciences (CAS)[XDA27010404] ; Shanghai Municipal Science and Technology Major Project[2021SHZDZX] ; Youth Innovation Promotion Association of CAS.
WOS关键词	TIMING-DEPENDENT PLASTICITY ; PYRAMIDAL NEURONS ; MODEL ; SPREAD
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:001025588300001
资助机构	Strategic Priority Research Program of the Chinese Academy of Sciences (CAS) ; Shanghai Municipal Science and Technology Major Project ; Youth Innovation Promotion Association of CAS.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53621]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者	Zhang, Tielin; Xu, Bo
作者单位	1.Chinese Acad Sci CASIA, Inst Automat, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China 3.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Tielin,Wang, Qingyu,Xu, Bo. Self-Lateral Propagation Elevates Synaptic Modifications in Spiking Neural Networks for the Efficient Spatial and Temporal Classification[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:13.
APA	Zhang, Tielin,Wang, Qingyu,&Xu, Bo.(2023).Self-Lateral Propagation Elevates Synaptic Modifications in Spiking Neural Networks for the Efficient Spatial and Temporal Classification.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13.
MLA	Zhang, Tielin,et al."Self-Lateral Propagation Elevates Synaptic Modifications in Spiking Neural Networks for the Efficient Spatial and Temporal Classification".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):13.