中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Emergence of brain-inspired small-world spiking neural network through neuroevolution

文献类型:期刊论文

作者Pan, Wenxuan1,2; Zhao, Feifei1; Han, Bing1,2; Dong, Yiting1,3; Zeng, Yi1,2,3,4
刊名ISCIENCE
出版日期2024-02-16
卷号27期号:2页码:16
DOI10.1016/j.isci.2024.108845
通讯作者Zeng, Yi(yi.zeng@ia.ac.cn)
英文摘要Studies suggest that the brain's high efficiency and low energy consumption may be closely related to its small -world topology and critical dynamics. However, existing efforts on the performance -oriented structural evolution of spiking neural networks (SNNs) are time-consuming and ignore the core structural properties of the brain. Here, we introduce a multi -objective Evolutionary Liquid State Machine (ELSM), which blends the small -world coefficient and criticality to evolve models and guide the emergence of brain -inspired, efficient structures. Experiments reveal ELSM's consistent and comparable performance, achieving 97.23% on NMNIST and outperforming LSM models on MNIST and FashionMNIST with 98.12% and 88.81% accuracies, respectively. Further analysis shows its versatility and spontaneous evolution of topologies such as hub nodes, short paths, long-tailed degree distributions, and numerous communities. This study evolves recurrent spiking neural networks into brain -inspired energy -efficient structures, showcasing versatility in multiple tasks and potential for adaptive general artificial intelligence.
WOS关键词NEURONS ; ARCHITECTURE ; FRAMEWORK
资助项目National Key Research and Development Program[2020AAA0107800] ; National Natural Science Foundation of China[62106261]
WOS研究方向Science & Technology - Other Topics
语种英语
WOS记录号WOS:001178671500001
出版者CELL PRESS
资助机构National Key Research and Development Program ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/57933]  
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.Chinese Acad Sci, Inst Automat, Brain Inspired Cognit Intelligence Lab, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China
3.Univ Chinese Acad Sci, Sch Future Technol, Beijing 101408, Peoples R China
4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
推荐引用方式
GB/T 7714
Pan, Wenxuan,Zhao, Feifei,Han, Bing,et al. Emergence of brain-inspired small-world spiking neural network through neuroevolution[J]. ISCIENCE,2024,27(2):16.
APA Pan, Wenxuan,Zhao, Feifei,Han, Bing,Dong, Yiting,&Zeng, Yi.(2024).Emergence of brain-inspired small-world spiking neural network through neuroevolution.ISCIENCE,27(2),16.
MLA Pan, Wenxuan,et al."Emergence of brain-inspired small-world spiking neural network through neuroevolution".ISCIENCE 27.2(2024):16.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。