Research on optimization method of convolutional nerual network

doi:10.1109/ELTECH.2018.8401481

CORC > 西安光学精密机械研究所 > 中国科学院西安光学精密机械研究所 > 光电测量技术实验室

	Research on optimization method of convolutional nerual network
	Feng, Xubin 1,2; Su, Xiuqin 1; Yan, Minqi 1; Xie, Meilin 1; Liu, Peng 1; Lian, Xuezheng 1; Jing, Feng 1
	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
内容类型	会议论文
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.