Spiking CapsNet: A spiking neural network with a biologically plausible routing rule between capsules

doi:10.1016/j.ins.2022.07.152

CORC > 自动化研究所 > 中国科学院自动化研究所 > 类脑智能研究中心 > 类脑认知计算

	Spiking CapsNet: A spiking neural network with a biologically plausible routing rule between capsules
	Zhao, Dongcheng 2,4; Li, Yang 2,3,4; Zeng, Yi 1,2,3,4,5; Wang, Jihang 2,3,4; Zhang, Qian 2,3,4
刊名	INFORMATION SCIENCES
	2022-09-01
卷号	610 页码:1-13
关键词	Spiking Neural Network Capsual Neural Netowrk Biologically Plausible Routing Noise Robustness Affine Transformation Robustness
ISSN号	0020-0255
DOI	10.1016/j.ins.2022.07.152
通讯作者	Zeng, Yi(yi.zeng@ia.ac.cn)
英文摘要	Spiking neural network (SNN) has attracted much attention due to its powerful spatiotemporal information representation ability. Capsule Neural Network (CapsNet) does well in assembling and coupling features of different network layers. Here, we propose Spiking CapsNet by combining spiking neurons and capsule structures. In addition, we propose a more biologically plausible Spike Timing Dependent Plasticity routing mechanism. The coupling ability is further improved by fully considering the spatio-temporal relationship between spiking capsules of the low layer and the high layer. We have verified experiments on the MNIST, FashionMNIST, and CIFAR10 datasets. Our algorithm still shows comparable performance concerning other excellent SNNs with typical structures (convolutional, fully-connected) on these classification tasks. Our Spiking CapsNet combines SNN and CapsNet's strengths and shows strong robustness to noise and affine transformation. By adding different Salt-Pepper and Gaussian noise to the test dataset, the experimental results demonstrate that our algorithm is more resistant to noise than other approaches. As well, our Spiking CapsNet shows strong generalization to affine transformation on the AffNIST dataset. Our code is available at https://github.com/BrainCog-X/Brain-Cog. (C) 2022 The Author(s). Published by Elsevier Inc.
资助项目	National Key Research and Development Program[2020AAA0104305] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32070100]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER SCIENCE INC
WOS记录号	WOS:000848341500001
资助机构	National Key Research and Development Program ; Strategic Priority Research Program of the Chinese Academy of Sciences
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50041]
专题	类脑智能研究中心_类脑认知计算
通讯作者	Zeng, Yi
作者单位	1.CASIA, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Chinese Acad Sci CASIA, Inst Automat, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 4.CASIA, Res Ctr Brain Inspired Intelligence, Beijing, Peoples R China 5.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Dongcheng,Li, Yang,Zeng, Yi,et al. Spiking CapsNet: A spiking neural network with a biologically plausible routing rule between capsules[J]. INFORMATION SCIENCES,2022,610:1-13.
APA	Zhao, Dongcheng,Li, Yang,Zeng, Yi,Wang, Jihang,&Zhang, Qian.(2022).Spiking CapsNet: A spiking neural network with a biologically plausible routing rule between capsules.INFORMATION SCIENCES,610,1-13.
MLA	Zhao, Dongcheng,et al."Spiking CapsNet: A spiking neural network with a biologically plausible routing rule between capsules".INFORMATION SCIENCES 610(2022):1-13.