首页 | 官方网站   微博 | 高级检索  
     

卷积神经网络的研究进展综述
引用本文:杨斌,钟金英.卷积神经网络的研究进展综述[J].南华大学学报(自然科学版),2016,30(3):66-72.
作者姓名:杨斌  钟金英
作者单位:南华大学 电气工程学院,湖南 衡阳 421001,南华大学 电气工程学院,湖南 衡阳 421001
基金项目:南华大学青年英才支持计划基金资助项目(聘字2014-004号);国家自然科学基金资助项目(61102108);南华大学校内博士启动基金资助项目(2011XQD29);湖南省优秀博士学位论文基金资助项目(YB2013B039)
摘    要:深度学习(deep learning,DL)强大的建模和表征能力很好地解决了特征表达能力不足和维数灾难等模式识别方向的关键问题,受到各国学者的广泛关注.而仿生物视觉系统的卷积神经网络(convolutional neural network,CNN)是DL中最先成功的案例,其局部感受野、权值共享和降采样三个特点使之成为智能机器视觉领域的研究热点.对此,本文综述CNN最新研究成果,介绍其发展历程、最新理论模型及其在语音、图像和视频中的应用,并对CNN未来的发展潜力和发展方向进行了展望和总结.

关 键 词:深度学习  卷积神经网络  特征提取  智能识别
收稿时间:2016/4/5 0:00:00

Review of Convolution Neural Network
YANG Bin and ZHONG Jin-ying.Review of Convolution Neural Network[J].Journal of Nanhua University:Science and Technology,2016,30(3):66-72.
Authors:YANG Bin and ZHONG Jin-ying
Affiliation:School of Electrical Engineering,University of South China,Hengyang,Hunan 421001,China and School of Electrical Engineering,University of South China,Hengyang,Hunan 421001,China
Abstract:Deep learning theory has received extensive attention of scholars all over the world because of its powerful modeling and high representational abilities.It solved the key problems of pattern recognition,such as the insufficiency of expression ability and dimensionality curse.Convolutional neural network (CNN) is a successful component of deep learning,which imitates the biological vision system.Local receptive field,sharing weights and down sampling are three important characteristics of CNN which lead it to be the hotspot in the field of intelligent machine vision.Therefore,this paper summarizes the latest research works of CNN.Firstly,the history of CNN is introduced.Secondly,state-of-the-art modified models of CNN are reviewed.Then,the applications of CNN in speech,image and video processing are illustrated.Finally,the development trends of CNN are concluded.
Keywords:deep learning  convolutional neural network  feature extraction  intelligent recognition
本文献已被 CNKI 等数据库收录!
点击此处可从《南华大学学报(自然科学版)》浏览原始摘要信息
点击此处可从《南华大学学报(自然科学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号