尖峰神经网络的脑启发进化架构

Wenxuan Pan;Feifei Zhao;Zhuoya Zhao;Yi Zeng
{"title":"尖峰神经网络的脑启发进化架构","authors":"Wenxuan Pan;Feifei Zhao;Zhuoya Zhao;Yi Zeng","doi":"10.1109/TAI.2024.3407033","DOIUrl":null,"url":null,"abstract":"The intricate and distinctive evolutionary topology of the human brain enables it to execute multiple cognitive tasks simultaneously, and this automated evolutionary process of biological networks motivates our investigation into efficient architecture optimization for spiking neural networks (SNNs). Diverging from traditional manual-designed and hierarchical network architecture search (NAS), we advance the evolution of SNN architecture by integrating local, brain region-inspired modular structures with global cross-module connectivity. Locally, the brain region-inspired module consists of multiple neural motifs with excitatory and inhibitory connections; globally, free connections among modules, including long-term cross-module feedforward and feedback connections are evolved. We introduce an efficient multiobjective evolutionary algorithm that leverages a few-shot predictor, endowing SNNs with high performance and low energy consumption. Extensive experiments across both static (CIFAR10, CIFAR100) and neuromorphic (CIFAR10-DVS, DVS128-Gesture) datasets reveal that the proposed model significantly exhibits robustness while maintaining consistent and exceptional performance. This study pioneers in searching for optimal neural architectures for SNNs by integrating the human brain's advanced connectivity and modular organization into SNN optimization, thereby contributing valuable perspectives to the development of brain-inspired artificial intelligence.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5760-5770"},"PeriodicalIF":0.0000,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Brain-Inspired Evolutionary Architectures for Spiking Neural Networks\",\"authors\":\"Wenxuan Pan;Feifei Zhao;Zhuoya Zhao;Yi Zeng\",\"doi\":\"10.1109/TAI.2024.3407033\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The intricate and distinctive evolutionary topology of the human brain enables it to execute multiple cognitive tasks simultaneously, and this automated evolutionary process of biological networks motivates our investigation into efficient architecture optimization for spiking neural networks (SNNs). Diverging from traditional manual-designed and hierarchical network architecture search (NAS), we advance the evolution of SNN architecture by integrating local, brain region-inspired modular structures with global cross-module connectivity. Locally, the brain region-inspired module consists of multiple neural motifs with excitatory and inhibitory connections; globally, free connections among modules, including long-term cross-module feedforward and feedback connections are evolved. We introduce an efficient multiobjective evolutionary algorithm that leverages a few-shot predictor, endowing SNNs with high performance and low energy consumption. Extensive experiments across both static (CIFAR10, CIFAR100) and neuromorphic (CIFAR10-DVS, DVS128-Gesture) datasets reveal that the proposed model significantly exhibits robustness while maintaining consistent and exceptional performance. This study pioneers in searching for optimal neural architectures for SNNs by integrating the human brain's advanced connectivity and modular organization into SNN optimization, thereby contributing valuable perspectives to the development of brain-inspired artificial intelligence.\",\"PeriodicalId\":73305,\"journal\":{\"name\":\"IEEE transactions on artificial intelligence\",\"volume\":\"5 11\",\"pages\":\"5760-5770\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on artificial intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10542732/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on artificial intelligence","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10542732/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

人脑复杂而独特的进化拓扑结构使其能够同时执行多项认知任务,这种生物网络的自动进化过程促使我们对尖峰神经网络(SNN)的高效架构优化进行研究。与传统的人工设计和分层网络架构搜索(NAS)不同,我们通过整合局部脑区启发的模块结构和全局跨模块连接,推进尖峰神经网络架构的进化。从局部来看,受脑区启发的模块由具有兴奋和抑制连接的多个神经图案组成;从全局来看,模块之间的自由连接,包括长期的跨模块前馈和反馈连接得到了进化。我们引入了一种高效的多目标进化算法,该算法利用少量预测器,赋予 SNNs 高性能和低能耗。在静态(CIFAR10、CIFAR100)和神经形态(CIFAR10-DVS、DVS128-Gesture)数据集上进行的广泛实验表明,所提出的模型在保持稳定和卓越性能的同时,显著地表现出了鲁棒性。这项研究开创性地将人脑的高级连接性和模块化组织整合到 SNN 优化中,为 SNN 寻找最佳神经架构,从而为脑启发人工智能的发展提供了宝贵的视角。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Brain-Inspired Evolutionary Architectures for Spiking Neural Networks
The intricate and distinctive evolutionary topology of the human brain enables it to execute multiple cognitive tasks simultaneously, and this automated evolutionary process of biological networks motivates our investigation into efficient architecture optimization for spiking neural networks (SNNs). Diverging from traditional manual-designed and hierarchical network architecture search (NAS), we advance the evolution of SNN architecture by integrating local, brain region-inspired modular structures with global cross-module connectivity. Locally, the brain region-inspired module consists of multiple neural motifs with excitatory and inhibitory connections; globally, free connections among modules, including long-term cross-module feedforward and feedback connections are evolved. We introduce an efficient multiobjective evolutionary algorithm that leverages a few-shot predictor, endowing SNNs with high performance and low energy consumption. Extensive experiments across both static (CIFAR10, CIFAR100) and neuromorphic (CIFAR10-DVS, DVS128-Gesture) datasets reveal that the proposed model significantly exhibits robustness while maintaining consistent and exceptional performance. This study pioneers in searching for optimal neural architectures for SNNs by integrating the human brain's advanced connectivity and modular organization into SNN optimization, thereby contributing valuable perspectives to the development of brain-inspired artificial intelligence.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
7.70
自引率
0.00%
发文量
0
期刊最新文献
Table of Contents Front Cover IEEE Transactions on Artificial Intelligence Publication Information Table of Contents Front Cover
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1