中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 脑图谱与类脑智能实验室
  5. 脑网络组研究中心
A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule

文献类型：期刊论文

作者Hao, Yunzhe1,2; Huang, Xuhui2; Dong, Meng2; Xu, Bo1,2,3
刊名NEURAL NETWORKS
出版日期2020
卷号121页码:387-395
关键词Spiking neural networks Dopamine-modulated spike-timing dependent plasticity Pattern recognition Supervised learning Biologically plausibility
ISSN号0893-6080
DOI10.1016/j.neunet.2019.09.007
通讯作者Huang, Xuhui(xuhui.huang@ia.ac.cn) ; Xu, Bo(xubo@ia.ac.cn)
英文摘要Spiking neural networks (SNNs) possess energy-efficient potential due to event-based computation. However, supervised training of SNNs remains a challenge as spike activities are non-differentiable. Previous SNNs training methods can be generally categorized into two basic classes, i.e., backpropagation-like training methods and plasticity-based learning methods. The former methods are dependent on energy-inefficient real-valued computation and non-local transmission, as also required in artificial neural networks (ANNs), whereas the latter are either considered to be biologically implausible or exhibit poor performance. Hence, biologically plausible (bio-plausible) high-performance supervised learning (SL) methods for SNNs remain deficient. In this paper, we proposed a novel bioplausible SNN model for SL based on the symmetric spike-timing dependent plasticity (sym-STDP) rule found in neuroscience. By combining the sym-STDP rule with bio-plausible synaptic scaling and intrinsic plasticity of the dynamic threshold, our SNN model implemented SL well and achieved good performance in the benchmark recognition task (MNIST dataset). To reveal the underlying mechanism of our SL model, we visualized both layer-based activities and synaptic weights using the t-distributed stochastic neighbor embedding (t-SNE) method after training and found that they were well clustered, thereby demonstrating excellent classification ability. Furthermore, to verify the robustness of our model, we trained it on another more realistic dataset (Fashion-MNIST), which also showed good performance. As the learning rules were bio-plausible and based purely on local spike events, our model could be easily applied to neuromorphic hardware for online training and may be helpful for understanding SL information processing at the synaptic level in biological neural systems. (C) 2019 Elsevier Ltd. All rights reserved.
WOS关键词TIMING-DEPENDENT PLASTICITY ; DOPAMINERGIC MODULATION ; VISUAL-CORTEX ; HOMEOSTASIS ; REWARD ; ENERGY
资助项目National Natural Science Foundation of China[11505283] ; Beijing Brain Science Project, China[Z181100001518006] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32070000]
WOS研究方向Computer Science ; Neurosciences & Neurology
语种英语
WOS记录号WOS:000500922700030
出版者PERGAMON-ELSEVIER SCIENCE LTD
资助机构National Natural Science Foundation of China ; Beijing Brain Science Project, China ; Strategic Priority Research Program of the Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/29427]  
专题自动化研究所_脑网络组研究中心
数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者Huang, Xuhui; Xu, Bo
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China
3.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Hao, Yunzhe,Huang, Xuhui,Dong, Meng,et al. A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule[J]. NEURAL NETWORKS,2020,121:387-395.
APA Hao, Yunzhe,Huang, Xuhui,Dong, Meng,&Xu, Bo.(2020).A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule.NEURAL NETWORKS,121,387-395.
MLA Hao, Yunzhe,et al."A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule".NEURAL NETWORKS 121(2020):387-395.

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。