Neuronal-Plasticity and Reward-Propagation Improved Recurrent Spiking Neural Networks

doi:10.3389/fnins.2021.654786

	Neuronal-Plasticity and Reward-Propagation Improved Recurrent Spiking Neural Networks
	Jia, Shuncheng 1,2; Zhang, Tielin1,2 ; Cheng, Xiang 1,2; Liu, Hongxing 1,3; Xu, Bo1,2,4
发表期刊	FRONTIERS IN NEUROSCIENCE
	2021-03-12
卷号	15 页码:11
通讯作者	Zhang, Tielin(tielin.zhang@ia.ac.cn) ; Xu, Bo(xubo@ia.ac.cn)
摘要	Different types of dynamics and plasticity principles found through natural neural networks have been well-applied on Spiking neural networks (SNNs) because of their biologically-plausible efficient and robust computations compared to their counterpart deep neural networks (DNNs). Here, we further propose a special Neuronal-plasticity and Reward-propagation improved Recurrent SNN (NRR-SNN). The historically-related adaptive threshold with two channels is highlighted as important neuronal plasticity for increasing the neuronal dynamics, and then global labels instead of errors are used as a reward for the paralleling gradient propagation. Besides, a recurrent loop with proper sparseness is designed for robust computation. Higher accuracy and stronger robust computation are achieved on two sequential datasets (i.e., TIDigits and TIMIT datasets), which to some extent, shows the power of the proposed NRR-SNN with biologically-plausible improvements.
关键词	spiking neural network neuronal plasticity synaptic plasticity reward propagation sparse connections
DOI	10.3389/fnins.2021.654786
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2020AAA0104305] ; National Natural Science Foundation of China[61806195] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32070100] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA27010404] ; Beijing Brain Science Project[Z181100001518006]
项目资助者	National Key R&D Program of China ; National Natural Science Foundation of China ; Strategic Priority Research Program of the Chinese Academy of Sciences ; Beijing Brain Science Project
WOS研究方向	Neurosciences & Neurology
WOS类目	Neurosciences
WOS记录号	WOS:000632907700001
出版者	FRONTIERS MEDIA SA
七大方向——子方向分类	类脑模型与计算
引用统计	被引频次：7[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/173211/44004
专题	复杂系统认知与决策实验室_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, Res Ctr Brain Inspired Intelligence, Beijing, Peoples R China 2.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing, Peoples R China 3.Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Jia, Shuncheng,Zhang, Tielin,Cheng, Xiang,et al. Neuronal-Plasticity and Reward-Propagation Improved Recurrent Spiking Neural Networks[J]. FRONTIERS IN NEUROSCIENCE,2021,15:11.
APA	Jia, Shuncheng,Zhang, Tielin,Cheng, Xiang,Liu, Hongxing,&Xu, Bo.(2021).Neuronal-Plasticity and Reward-Propagation Improved Recurrent Spiking Neural Networks.FRONTIERS IN NEUROSCIENCE,15,11.
MLA	Jia, Shuncheng,et al."Neuronal-Plasticity and Reward-Propagation Improved Recurrent Spiking Neural Networks".FRONTIERS IN NEUROSCIENCE 15(2021):11.