SIA OpenIR  > 光电信息技术研究室
Research on Optimization Method of Deep Neural Network
Liu PF(刘鹏飞); Zhao HC(赵怀慈); Cao FD(曹飞道)
Conference DateJuly 23-25, 2017
Conference PlaceChangchun, China
Author of SourceChinese Society for Optical Engineering (CSOE)
Source PublicationProceedings SPIE 10605, LIDAR Imaging Detection and Target Recognition 2017
Publication PlaceBellingham, USA
Indexed ByEI ; CPCI(ISTP)
EI Accession number20181705046915
WOS IDWOS:000426279000096
Contribution Rank1
KeywordDeep Neural Network Object Classification Over-fitting Loss Function
AbstractImage recognition technology has been widely applied and played an important role in various fields nowadays. Because of multi-layer structure of deep network can use a more concise way to express complex functions, deep neural network (DNN) will be applied to the image recognition to improve the accuracy of image classification. Analysis the existing problems of deep neural network. Then put forward new approaches to solve the gradient vanishing and over-fitting problems. The experimental results which verified on the MNIST, show that our proposed approaches can improve the classification accuracy greatly and accelerate the convergence speed. Compared to support vector machine (SVM), the optimized model of the neural network is not only effective, but also converged quickly.
Citation statistics
Document Type会议论文
Corresponding AuthorZhao HC(赵怀慈)
Affiliation1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016
2.University of Chinese Academy of Sciences, Beijing 100049
3.Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang 110016
4.The Key Lab of Image Understanding and Computer Vision, Liaoning Province, Shenyang 110016
Recommended Citation
GB/T 7714
Liu PF,Zhao HC,Cao FD. Research on Optimization Method of Deep Neural Network[C]//Chinese Society for Optical Engineering (CSOE). Bellingham, USA:SPIE,2017:1-6.
Files in This Item:
File Name/Size DocType Version Access License
Research on Optimiza(749KB)会议论文 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu PF(刘鹏飞)]'s Articles
[Zhao HC(赵怀慈)]'s Articles
[Cao FD(曹飞道)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu PF(刘鹏飞)]'s Articles
[Zhao HC(赵怀慈)]'s Articles
[Cao FD(曹飞道)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu PF(刘鹏飞)]'s Articles
[Zhao HC(赵怀慈)]'s Articles
[Cao FD(曹飞道)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Research on Optimization Method of Deep Neural Network.pdf
Format: Adobe PDF
All comments (0)
No comment.

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