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. 类脑认知计算
Toward a Brain-Inspired Developmental Neural Network Based on Dendritic Spine Dynamics

文献类型：期刊论文

作者Zhao, Feifei2; Zeng, Yi1,2,3,4,5; Bai, Jun2
刊名NEURAL COMPUTATION
出版日期2021-12-15
卷号34期号:1页码:172-189
ISSN号0899-7667
DOI10.1162/neco_a_01448
通讯作者Zeng, Yi(yi.zeng@ia.ac.cn)
英文摘要Neural networks with a large number of parameters are prone to overfitting problems when trained on a relatively small training set. Introducing weight penalties of regularization is a promising technique for solving this problem. Taking inspiration from the dynamic plasticity of dendritic spines, which plays an important role in the maintenance of memory, this letter proposes a brain-inspired developmental neural network based on dendritic spine dynamics (BDNN-dsd). The dynamic structure changes of dendritic spines include appearing, enlarging, shrinking, and disappearing. Such spine plasticity depends on synaptic activity and can be modulated by experiences-in particular, long-lasting synaptic enhancement/suppression (LTP/LTD), coupled with synapse formation (or enlargement)/elimination (or shrinkage), respectively. Subsequently, spine density characterizes an approximate estimate of the total number of synapses between neurons. Motivated by this, we constrain the weight to a tunable bound that can be adaptively modulated based on synaptic activity. Dynamic weight bound could limit the relatively redundant synapses and facilitate the contributing synapses. Extensive experiments demonstrate the effectiveness of our method on classification tasks of different complexity with the MNIST, Fashion MNIST, and CIFAR-10 data sets. Furthermore, compared to dropout and L2 regularization algorithms, our method can improve the network convergence rate and classification performance even for a compact network.
WOS关键词RECOGNITION ; STABILITY
资助项目National Key Research and Development Program[2020AAA107800] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32070100] ; Beijing Municipal Commission of Science and Technology[Z181100001518006] ; Key Research Program of Frontier Sciences, Chinese Academy of Sciences[ZDBS-LY-JSC013] ; Beijing Academy of Artificial Intelligence
WOS研究方向Computer Science ; Neurosciences & Neurology
语种英语
WOS记录号WOS:000730790000006
出版者MIT PRESS
资助机构National Key Research and Development Program ; Strategic Priority Research Program of the Chinese Academy of Sciences ; Beijing Municipal Commission of Science and Technology ; Key Research Program of Frontier Sciences, Chinese Academy of Sciences ; Beijing Academy of Artificial Intelligence
源URL[http://ir.ia.ac.cn/handle/173211/46854]  
专题类脑智能研究中心_类脑认知计算
通讯作者Zeng, Yi
作者单位1.Univ Chinese Acad Sci, Sch Future Technol, Beijing 10049, Peoples R China
2.Chinese Acad Sci, Res Ctr Brain Inspired Intelligence, Inst Automat, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 10049, Peoples R China
4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
5.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Zhao, Feifei,Zeng, Yi,Bai, Jun. Toward a Brain-Inspired Developmental Neural Network Based on Dendritic Spine Dynamics[J]. NEURAL COMPUTATION,2021,34(1):172-189.
APA Zhao, Feifei,Zeng, Yi,&Bai, Jun.(2021).Toward a Brain-Inspired Developmental Neural Network Based on Dendritic Spine Dynamics.NEURAL COMPUTATION,34(1),172-189.
MLA Zhao, Feifei,et al."Toward a Brain-Inspired Developmental Neural Network Based on Dendritic Spine Dynamics".NEURAL COMPUTATION 34.1(2021):172-189.

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。