Research on Optimization Method of Deep Neural Network
文献类型：会议论文
| 作者 | Zhao HC(赵怀慈) ; Liu PF(刘鹏飞); Cao FD(曹飞道)
|
| 出版日期 | 2017 |
| 会议名称 | LIDAR IMAGING DETECTION AND TARGET RECOGNITION 2017 |
| 会议日期 | July 23-25, 2017 |
| 会议地点 | Changchun, China |
| 关键词 | Deep neural network object classification over-fitting loss function |
| 页码 | 1-6 |
| 通讯作者 | Zhao HC(赵怀慈) |
| 中文摘要 | Image 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. |
| 收录类别 | EI ; CPCI（ISTP） |
| 产权排序 | 1 |
| 会议主办者 | Chinese Society for Optical Engineering (CSOE) |
| 会议录 | Proceedings SPIE 10605, LIDAR Imaging Detection and Target Recognition 2017
 |
| 会议录出版者 | SPIE |
| 会议录出版地 | Bellingham, USA |
| 语种 | 英语 |
| ISSN号 | 0277-786X |
| WOS记录号 | WOS:000426279000096 |
| 源URL | [http://ir.sia.cn/handle/173321/21306]  |
| 专题 | 沈阳自动化研究所_光电信息技术研究室 |
| 作者单位 | 1.Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang 110016 2.University of Chinese Academy of Sciences, Beijing 100049 3.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016 4.The Key Lab of Image Understanding and Computer Vision, Liaoning Province, Shenyang 110016 |
| 推荐引用方式 GB/T 7714 | Zhao HC,Liu PF,Cao FD. Research on Optimization Method of Deep Neural Network[C]. 见:LIDAR IMAGING DETECTION AND TARGET RECOGNITION 2017. Changchun, China. July 23-25, 2017. |
入库方式： OAI收割
来源：沈阳自动化研究所
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。