摘要
回顾了卷积神经网络的发展历程,介绍了卷积神经网络的基本运算单元。在查阅大量资料基础上,重点介绍了有代表性的AlexNet、VGGNet、GoogLeNet、ResNet等,对他们所用到的技术进行剖析,归纳、总结、分析其优缺点,并指出卷积神经网络未来的研究方向。
This paper reviews the development of convolutional neural networks,and introduces the basic operation unit of convolutional neural networks.On the basis of consulting a large amount of information,this paper focuses on the representative convolutional neural networks such as AlexNet,VGGNet,GoogLeNet and ResNet etc.,analyzes the technologies they used,summarizes and analyzes their advantages and disadvantages,and points out the future research direction of convolutional neural networks.
作者
李炳臻
刘克
顾佼佼
姜文志
Li Bingzhen;Liu Ke;Gu Jiaojiao;Jiang Wenzhi(95668 unit of PLA,Kunming,Yunnan 650000,China;Naval Aviation University,Coast Guard Academy)
出处
《计算机时代》
2021年第4期8-12,17,共6页
Computer Era