CASIA OpenIR  > 类脑智能研究中心  > 神经计算及脑机交互
Towards a Brain-inspired Developmental Neural Network by Adaptive Synaptic Pruning
Zhao FF(赵菲菲)1,2; Zhang TL(张铁林)1; Ceng Y(曾毅)1,2,3; Xu B(徐波)1,2,3; Feifei Zhao, Yi Zeng, Tielin Zhang
2017
Conference NameThe 24th international Conference on Neural Information Processing (ICONIP 2017)
Conference DateNovember 14-18
Conference PlaceGuangzhou, China, 2017.
AbstractIt is widely accepted that appropriate network topology should be empirically predefined before training a specific neural network learning task. However, in most cases, these carefully designed networks are easily falling into two kinds of dilemmas: 1) When the data is not enough to train the network well, it will get an underfitting result. 2)When networks have learned too much patterns, they are likely to lead to an overfitting result and have a poor performance on processing new data or transferring to other tasks. Inspired by the synaptic pruning characteristics of the human brain, we propose a brain-inspired developmental neural network (BDNN) algorithm by adaptive synaptic pruning (BDNN-sp) which could get rid of the overfitting and underfitting. The BDNN-sp algorithm adaptively modulates network topology by pruning useless neurons dynamically. In addition, the evolutional optimization method makes the network stop on an appropriate network topology with the best consideration of accuracy and adaptability. Experimental results indicate that the proposed algorithm could automatically find the optimal network topology and the network complexity could adaptively increase along with the increase of task complexity. Compared to the traditional topology-predefined networks, trained BDNN-sp has the similar accuracy but better transfer learning abilities.
KeywordBrain-inspired Developmental Neural Network Brain-inspired Pruning Rules Structural Plasticity Network Adaptability Synaptic Pruning
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/22083
Collection类脑智能研究中心_神经计算及脑机交互
Corresponding AuthorFeifei Zhao, Yi Zeng, Tielin Zhang
Affiliation1.Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.University of Chinese Academy of Sciences, Beijing, China
3.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China
Recommended Citation
GB/T 7714
Zhao FF,Zhang TL,Ceng Y,et al. Towards a Brain-inspired Developmental Neural Network by Adaptive Synaptic Pruning[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
Towards a Brain-insp(386KB)会议论文 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
[Zhao FF(赵菲菲)]'s Articles
[Zhang TL(张铁林)]'s Articles
[Ceng Y(曾毅)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao FF(赵菲菲)]'s Articles
[Zhang TL(张铁林)]'s Articles
[Ceng Y(曾毅)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao FF(赵菲菲)]'s Articles
[Zhang TL(张铁林)]'s Articles
[Ceng Y(曾毅)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Towards a Brain-inspired Developmental Neural Network by Adaptive Synaptic Pruning.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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