CASIA OpenIR  > 类脑智能研究中心
A Curiosity-Based Learning Method for Spiking Neural Networks
Mengting Shi; Tielin Zhang; Yi Zeng
Source PublicationFrontiers in Computational Neuroscience
ISSN1662-5188
2020-02
Volume14Issue:14Pages:7
Corresponding AuthorZeng, Yi(yi.zeng@ia.ac.cn)
Abstract

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.

KeywordCuriosity Spiking Neural Network Novelty Stdp Voltage-driven Plasticity-centric Snn
MOST Discipline Catalogue工学
DOI10.3389/fncom.2020.00007
WOS KeywordREWARD CIRCUITRY ; MODEL
URL查看原文
Indexed BySCIE
Language英语
Funding ProjectStrategic 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)
Funding OrganizationStrategic 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 Research AreaMathematical & Computational Biology ; Neurosciences & Neurology
WOS SubjectMathematical & Computational Biology ; Neurosciences
WOS IDWOS:000518658700001
PublisherFRONTIERS MEDIA SA
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/38527
Collection类脑智能研究中心
Corresponding AuthorYi Zeng
Recommended Citation
GB/T 7714
Mengting Shi,Tielin Zhang,Yi Zeng. A Curiosity-Based Learning Method for Spiking Neural Networks[J]. Frontiers in Computational Neuroscience,2020,14(14):7.
APA Mengting Shi,Tielin Zhang,&Yi Zeng.(2020).A Curiosity-Based Learning Method for Spiking Neural Networks.Frontiers in Computational Neuroscience,14(14),7.
MLA Mengting Shi,et al."A Curiosity-Based Learning Method for Spiking Neural Networks".Frontiers in Computational Neuroscience 14.14(2020):7.
Files in This Item: Download All
File Name/Size DocType Version Access License
fncom-14-00007-2.pdf(1349KB)期刊 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Mengting Shi]'s Articles
[Tielin Zhang]'s Articles
[Yi Zeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Mengting Shi]'s Articles
[Tielin Zhang]'s Articles
[Yi Zeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Mengting Shi]'s Articles
[Tielin Zhang]'s Articles
[Yi Zeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: fncom-14-00007-2.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.