CASIA OpenIR  > 类脑智能研究中心  > 神经计算及脑机交互
Brain-inspired Balanced Tuning for Spiking Neural Networks
Zhang TL(张铁林)1,3; Ceng Y(曾毅)1,2,3,4,5; Zhao DC(赵东城)1,2,3; Xu B(徐波)1,2,3,5; Tielin Zhang, Yi Zeng
2018-07
会议名称The 27th International Joint Conference on Artificial Intelligence (IJCAI 2018)
会议日期July 13-19, 2018
会议地点Stockholm, Sweden
摘要Due to the nature of Spiking Neural Networks (SNNs), it is challenging to be trained by biologically plausible learning principles. The multi-layered SNNs are with non-differential neurons, temporary-centric synapses, which make them nearly impossible to be directly tuned by back propagation. Here we propose an alternative biological inspired balanced tuning approach to train SNNs. The approach contains three main inspirations from the brain: Firstly, the biological network will usually be trained towards the state where the temporal update of variables are equilibrium (e.g. membrane potential); Secondly, specific proportions of excitatory and inhibitory neurons usually contribute to stable representations; Thirdly, the short-term plasticity (STP) is a general principle to keep the input and output of synapses balanced towards a better learning convergence. With these inspirations, we train SNNs with three steps: Firstly, the SNN model is trained with three brain-inspired principles; then weakly supervised learning is used to tune the membrane potential in the final layer for network classification; finally the learned information is consolidated from membrane potential into the weights of synapses by Spike-Timing Dependent Plasticity (STDP). The proposed approach is verified on the MNIST hand-written digit recognition dataset and the performance (the accuracy of 98.64%) indicates that the ideas of balancing state could indeed improve the learning ability of SNNs, which shows the power of proposed brain-inspired approach on the tuning of biological plausible SNNs.
关键词Spiking Neural Network
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/22080
专题类脑智能研究中心_神经计算及脑机交互
通讯作者Tielin Zhang, Yi Zeng
作者单位1.Institute of Automation, Chinese Academy of Sciences (CAS), China
2.University of Chinese Academy of Sciences, China
3.Research Center for Brain-inspired Intelligence, Institute of Automation, CAS, China
4.National Laboratory of Pattern Recognition, Institute of Automation, CAS, China
5.Center for Excellence in Brain Science and Intelligence Technology, CAS, China
推荐引用方式
GB/T 7714
Zhang TL,Ceng Y,Zhao DC,et al. Brain-inspired Balanced Tuning for Spiking Neural Networks[C],2018.
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
ijcai18-Brain-inspir(609KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang TL(张铁林)]的文章
[Ceng Y(曾毅)]的文章
[Zhao DC(赵东城)]的文章
百度学术
百度学术中相似的文章
[Zhang TL(张铁林)]的文章
[Ceng Y(曾毅)]的文章
[Zhao DC(赵东城)]的文章
必应学术
必应学术中相似的文章
[Zhang TL(张铁林)]的文章
[Ceng Y(曾毅)]的文章
[Zhao DC(赵东城)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: ijcai18-Brain-inspired Balanced Tuning for Spiking Neural Networks.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。