卷积神经网络综述

被引:161
作者
刘健
袁谦
吴广
喻晓
机构
[1] 浙江省电子信息产品检验所
关键词
深度学习; 卷积神经网络; 网络结构; 训练方法;
D O I
10.16644/j.cnki.cn33-1094/tp.2018.11.005
中图分类号
TP183 [人工神经网络与计算];
学科分类号
140502 [人工智能];
摘要
卷积神经网络作为深度学习的一种经典而广泛应用的结构,克服了过去人工智能中被认为难以解决的一些问题。卷积神经网络的局部连接、权值共享及下采样操作等特性使之可以有效地降低网络的复杂度,减少训练参数的数目,使模型对平移、扭曲、缩放具有一定程度的不变性,并具有强鲁棒性和容错能力,也易于训练和优化。文章介绍了卷积神经网络的训练方法,开源工具,及在图像分类领域中的一些应用,给出了卷积神经待解决的问题及展望。
引用
收藏
页码:19 / 23
页数:5
相关论文
共 9 条
[1]
Going deeper with convolutions..Szegedy C;Liu W;.Competer Vision and Pattern Recognition.2015,
[2]
Representation Learning: A Review and New Perspectives [J].
Bengio, Yoshua ;
Courville, Aaron ;
Vincent, Pascal .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (08) :1798-1828
[3]
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion..[J].Pascal Vincent;Hugo Larochelle;Isabelle Lajoie;Yoshua Bengio;Pierre-Antoine Manzagol.Journal of Machine Learning Research.2010,
[4]
Learning Deep Architectures for AI [J].
Bengio, Yoshua .
FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2009, 2 (01) :1-127
[5]
A fast learning algorithm for deep belief nets [J].
Hinton, Geoffrey E. ;
Osindero, Simon ;
Teh, Yee-Whye .
NEURAL COMPUTATION, 2006, 18 (07) :1527-1554
[6]
Gradient-based learning applied to document recognition [J].
Lecun, Y ;
Bottou, L ;
Bengio, Y ;
Haffner, P .
PROCEEDINGS OF THE IEEE, 1998, 86 (11) :2278-2324
[7]
Backpropagation Applied to Handwritten Zip Code Recognition [J].
LeCun, Y. ;
Boser, B. ;
Denker, J. S. ;
Henderson, D. ;
Howard, R. E. ;
Hubbard, W. ;
Jackel, L. D. .
NEURAL COMPUTATION, 1989, 1 (04) :541-551
[8]
LEARNING REPRESENTATIONS BY BACK-PROPAGATING ERRORS [J].
RUMELHART, DE ;
HINTON, GE ;
WILLIAMS, RJ .
NATURE, 1986, 323 (6088) :533-536
[9]
A logical calculus of the ideas immanent in nervous activity.[J].Warren S. McCulloch;Walter Pitts.The Bulletin of Mathematical Biophysics.1943, 4