首页 | 本学科首页   官方微博 | 高级检索  
     

基于自编码算法的深度学习综述
引用本文:崔广新,李殿奎.基于自编码算法的深度学习综述[J].计算机系统应用,2018,27(9):47-51.
作者姓名:崔广新  李殿奎
作者单位:佳木斯大学 信息电子技术学院, 佳木斯 154007,佳木斯大学 信息电子技术学院, 佳木斯 154007
基金项目:2017年黑龙江省教育科研专项(2017-0001)
摘    要:深度学习是机器学习的一个分支,开创了神经网络发展的新纪元.自编码算法作为深度学习结构的重要组成部分,在无监督学习及非线性特征提取过程中起到了至关重要的作用.首先介绍自编码算法的基本概念及原理,然后介绍基于自编码算法的改进算法,最后列举了自编码算法在若干领域应用的知名案例和发展趋势.

关 键 词:机器学习  深度学习  自编码算法  无监督学习  神经网络
收稿时间:2018/1/9 0:00:00
修稿时间:2018/1/31 0:00:00

Overview on Deep Learning Based on Automatic Encoder Algorithms
CUI Guang-Xin and LI Dian-Kui.Overview on Deep Learning Based on Automatic Encoder Algorithms[J].Computer Systems& Applications,2018,27(9):47-51.
Authors:CUI Guang-Xin and LI Dian-Kui
Affiliation:College of Information Science and Electronic Technology, Jiamusi University, Jiamusi 154007, China and College of Information Science and Electronic Technology, Jiamusi University, Jiamusi 154007, China
Abstract:Deep learning is a branch of machine learning, creating a new era in the development of neural networks. As an important part of deep learning structure, self-coding algorithm plays a crucial role in unsupervised learning and nonlinear feature extraction. Firstly, the basic concepts and principles of self-encoding algorithm are introduced. Then, the improved algorithm based on self-encoding algorithm is presented. Finally, the well-known cases and development trends of self-encoding algorithm applied in several fields are elaborated.
Keywords:machine learning  deep learning  automatic encoder  unsupervised learning  neural networks
点击此处可从《计算机系统应用》浏览原始摘要信息
点击此处可从《计算机系统应用》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