Knowledge Commons of Institute of Automation,CAS
A Curiosity-Based Learning Method for Spiking Neural Networks | |
Shi, Mengting; Zhang, Tielin; Zeng, Yi | |
发表期刊 | Frontiers in Computational Neuroscience |
ISSN | 1662-5188 |
2020-02 | |
卷号 | 14期号:14页码:7 |
摘要 | Spiking Neural Networks (SNNs) have shown favorable performance recently. Nonetheless, the time-consuming computation on neuron level and complex optimization limit their real-time application. Curiosity has shown great performance in brain learning, which helps biological brains grasp new knowledge efficiently and actively. Inspired by this leaning mechanism, we propose a curiosity-based SNN (CBSNN) model, which contains four main learning processes. Firstly, the network is trained with biologically plausible plasticity principles to get the novelty estimations of all samples in only one epoch; secondly, the CBSNN begins to repeatedly learn the samples whose novelty estimations exceed the novelty threshold and dynamically update the novelty estimations of samples according to the learning results in five epochs; thirdly, in order to avoid the overfitting of the novel samples and forgetting of the learned samples, CBSNN retrains all samples in one epoch; finally, step two and step three are periodically taken until network convergence. Compared with the state-of-the-art Voltage-driven Plasticity-centric SNN (VPSNN) under standard architecture, our model achieves a higher accuracy of 98.55% with only 54.95% of its computation cost on the MNIST hand-written digit recognition dataset. Similar conclusion can also be found out in other datasets, i.e., Iris, NETtalk, Fashion-MNIST, and CIFAR-10, respectively. More experiments and analysis further prove that such curiosity-based learning theory is helpful in improving the efficiency of SNNs. As far as we know, this is the first practical combination of the curiosity mechanism and SNN, and these improvements will make the realistic application of SNNs possible on more specific tasks within the von Neumann framework. |
关键词 | Curiosity Spiking Neural Network Novelty Stdp Voltage-driven Plasticity-centric Snn |
学科门类 | 工学 |
DOI | 10.3389/fncom.2020.00007 |
关键词[WOS] | REWARD CIRCUITRY ; MODEL |
URL | 查看原文 |
收录类别 | SCIE |
语种 | 英语 |
资助项目 | Strategic Priority Research Program of Chinese Academy of Sciences[XDB32070100] ; Beijing Municipality of Science and Technology[Z181100001518006] ; CETC Joint Fund[6141B08010103] ; Major Research Program of Shandong Province[2018CXGC1503] ; Beijing Natural Science Foundation[4184103] ; National Natural Science Foundation of China[61806195] ; Beijing Academy of Artificial Intelligence (BAAI) |
项目资助者 | Strategic Priority Research Program of Chinese Academy of Sciences ; Beijing Municipality of Science and Technology ; CETC Joint Fund ; Major Research Program of Shandong Province ; Beijing Natural Science Foundation ; National Natural Science Foundation of China ; Beijing Academy of Artificial Intelligence (BAAI) |
WOS研究方向 | Mathematical & Computational Biology ; Neurosciences & Neurology |
WOS类目 | Mathematical & Computational Biology ; Neurosciences |
WOS记录号 | WOS:000518658700001 |
出版者 | FRONTIERS MEDIA SA |
七大方向——子方向分类 | 类脑模型与计算 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/38527 |
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 | 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 |
推荐引用方式 GB/T 7714 | Shi, Mengting,Zhang, Tielin,Zeng, Yi. A Curiosity-Based Learning Method for Spiking Neural Networks[J]. Frontiers in Computational Neuroscience,2020,14(14):7. |
APA | Shi, Mengting,Zhang, Tielin,&Zeng, Yi.(2020).A Curiosity-Based Learning Method for Spiking Neural Networks.Frontiers in Computational Neuroscience,14(14),7. |
MLA | Shi, Mengting,et al."A Curiosity-Based Learning Method for Spiking Neural Networks".Frontiers in Computational Neuroscience 14.14(2020):7. |
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 | ||
fncom-14-00007-2.pdf(1349KB) | 期刊 | 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