Knowledge Commons of Institute of Automation,CAS
BSNN: Towards faster and better conversion of artificial neural networks to spiking neural networks with bistable neurons | |
Li, Yang1,2; Zhao, Dongcheng1; Zeng, Yi1,2,3,4 | |
发表期刊 | Frontiers in Neuroscience |
2022-10-12 | |
卷号 | 16页码:13 |
摘要 | The spiking neural network (SNN) computes and communicates information through discrete binary events. Recent work has achieved essential progress on an excellent performance by converting ANN to SNN. Due to the difference in information processing, the converted deep SNN usually suffers serious performance loss and large time delay. In this paper, we analyze the reasons for the performance loss and propose a novel bistable spiking neural network (BSNN) that addresses the problem of the phase lead and phase lag. Also, we design synchronous neurons (SN) to help efficiently improve performance when ResNet structure-based ANNs are converted. BSNN significantly improves the performance of the converted SNN by enabling more accurate delivery of information to the next layer after one cycle. Experimental results show that the proposed method only needs 1/4-1/10 of the time steps compared to previous work to achieve nearly lossless conversion. We demonstrate better ANN-SNN conversion for VGG16, ResNet20, and ResNet34 on challenging datasets including CIFAR-10 (95.16% top-1), CIFAR-100 (78.12% top-1), and ImageNet (72.64% top-1). |
关键词 | spiking neural network bistability neuromorphic computing image classification conversion |
DOI | 10.3389/fnins.2022.991851 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program ; Strategic Priority Research Program of the Chinese Academy of Sciences ; [2020AAA0107800] ; [XDB32070100] |
项目资助者 | National Key Research and Development Program ; Strategic Priority Research Program of the Chinese Academy of Sciences |
WOS研究方向 | Neurosciences & Neurology |
WOS类目 | Neurosciences |
WOS记录号 | WOS:000876692100001 |
出版者 | FRONTIERS MEDIA SA |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 类脑模型与计算 |
国重实验室规划方向分类 | 认知机理与类脑学习 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/50518 |
专题 | 脑图谱与类脑智能实验室_类脑认知计算 |
通讯作者 | Zeng, Yi |
作者单位 | 1.Research Center for Brain-Inspired Intelligence, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences 4.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
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; 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Li, Yang,Zhao, Dongcheng,Zeng, Yi. BSNN: Towards faster and better conversion of artificial neural networks to spiking neural networks with bistable neurons[J]. Frontiers in Neuroscience,2022,16:13. |
APA | Li, Yang,Zhao, Dongcheng,&Zeng, Yi.(2022).BSNN: Towards faster and better conversion of artificial neural networks to spiking neural networks with bistable neurons.Frontiers in Neuroscience,16,13. |
MLA | Li, Yang,et al."BSNN: Towards faster and better conversion of artificial neural networks to spiking neural networks with bistable neurons".Frontiers in Neuroscience 16(2022):13. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
fnins-16-991851.pdf(3930KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论