Brain-inspired neural circuit evolution for spiking neural networks

doi:10.1073/pnas.2218173120

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

	Brain-inspired neural circuit evolution for spiking neural networks
	Shen, Guobin 1,2; Zhao, Dongcheng 1; Dong, Yiting 1,2; Zeng, Yi 1,2,3,4
刊名	PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
	2023-09-26
卷号	120 期号:39 页码:10
关键词	brain-inspired neural circuit evolution spiking neural networks
ISSN号	0027-8424
DOI	10.1073/pnas.2218173120
通讯作者	Zeng, Yi(yi.zeng@ia.ac.cn)
英文摘要	In biological neural systems, different neurons are capable of self-organizing to form different neural circuits for achieving a variety of cognitive functions. However, the current design paradigm of spiking neural networks is based on structures derived from deep learning. Such structures are dominated by feedforward connections without taking into account different types of neurons, which significantly prevent spiking neural networks from realizing their potential on complex tasks. It remains an open challenge to apply the rich dynamical properties of biological neural circuits to model the structure of current spiking neural networks. This paper provides a more biologically plausible evolutionary space by combining feedforward and feedback connections with excitatory and inhibitory neurons. We exploit the local spiking behavior of neurons to adaptively evolve neural circuits such as forward excitation, forward inhibition, feedback inhibition, and lateral inhibition by the local law of spike-timing-dependent plasticity and update the synaptic weights in combination with the global error signals. By using the evolved neural circuits, we construct spiking neural networks for image classification and reinforcement learning tasks. Using the brain-inspired Neural circuit Evolution strategy (NeuEvo) with rich neural circuit types, the evolved spiking neural network greatly enhances capability on perception and reinforcement learning tasks. NeuEvo achieves state-of-the-art performance on CIFAR10, DVS-CIFAR10, DVS-Gesture, and N-Caltech101 datasets and achieves advanced performance on ImageNet. Combined with on-policy and off-policy deep reinforcement learning algorithms, it achieves comparable performance with artificial neural networks. The evolved spiking neural circuits lay the foundation for the evolution of complex networks with functions.
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32070100]
WOS研究方向	Science & Technology - Other Topics
语种	英语
出版者	NATL ACAD SCIENCES
WOS记录号	WOS:001141948400008
资助机构	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/173211/54819]
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.Univ Chinese Acad Sci, Sch Future Technol, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Shen, Guobin,Zhao, Dongcheng,Dong, Yiting,et al. Brain-inspired neural circuit evolution for spiking neural networks[J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA,2023,120(39):10.
APA	Shen, Guobin,Zhao, Dongcheng,Dong, Yiting,&Zeng, Yi.(2023).Brain-inspired neural circuit evolution for spiking neural networks.PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA,120(39),10.
MLA	Shen, Guobin,et al."Brain-inspired neural circuit evolution for spiking neural networks".PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA 120.39(2023):10.