Research on optimization method of convolutional nerual network
文献类型:会议论文
作者 | Feng, Xubin1,2; Su, Xiuqin1![]() ![]() |
出版日期 | 2018-06-29 |
会议日期 | 2018-05-23 |
会议地点 | Chengdu, China |
DOI | 10.1109/ELTECH.2018.8401481 |
页码 | 345-348 |
英文摘要 | With the improvement of computers' computation and storage performance, the deep learning technology, especially the convolutional neural network (CNN) has been widely used in many fields such as Computer Vision (CV), Natural Language Processing (NLP) and Automatic Speech Recognition (ASR). CNNs have become the state-of-The-Art technique in many vision tasks, such as image classification, object detection, etc. But the deep CNNs may make part of the kernels too thin by using parameterized convolution kernel to extract features. Therefore, this paper proposes a method to optimize CNNs by calculating the similarity coefficient between the feature maps. Experimental results showed that this method improved the training speed and the detecting speed with the accuracy been ensured. © 2018 IEEE. |
产权排序 | 1 |
会议录 | 2018 International Conference on Electronics Technology, ICET 2018
![]() |
会议录出版者 | Institute of Electrical and Electronics Engineers Inc. |
语种 | 英语 |
ISBN号 | 9781538657522 |
源URL | [http://ir.opt.ac.cn/handle/181661/30548] ![]() |
专题 | 西安光学精密机械研究所_光电测量技术实验室 |
作者单位 | 1.Photoelectric Tracking, Xi'An Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, China; 2.University of Chinese Academy of Sciences, China |
推荐引用方式 GB/T 7714 | Feng, Xubin,Su, Xiuqin,Yan, Minqi,et al. Research on optimization method of convolutional nerual network[C]. 见:. Chengdu, China. 2018-05-23. |
入库方式: OAI收割
来源:西安光学精密机械研究所
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。