Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)

The Principle and Application of Deep Learning Algorithm

Authors
Pengfei Hu, Hao Tang
Corresponding Author
Pengfei Hu
Available Online May 2018.
DOI
10.2991/ncce-18.2018.138How to use a DOI?
Keywords
deep learning, Restricted Boltzmann Machines, automatic coding machine.
Abstract

Deep learning is emerging as a multilayer neural network dimensionality reduction algorithm, the neural network model with multiple deep hidden layer through the formation of the high dimensional data of input layer feature extraction, to find a low dimensional nested data structure, the formation of more abstract effective executives said. Starting from the basic principle of deep learning algorithm, introduces the basic structure of single-layer network restricted Boltzmann deep learning algorithm and its training process. Finally, an example is given to illustrate the performance improvement of deep learning technology applied to handwritten digit recognition, and the deep learning technology is briefly summarized.

Copyright
© 2018, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
Series
Advances in Intelligent Systems Research
Publication Date
May 2018
ISBN
10.2991/ncce-18.2018.138
ISSN
1951-6851
DOI
10.2991/ncce-18.2018.138How to use a DOI?
Copyright
© 2018, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Pengfei Hu
AU  - Hao Tang
PY  - 2018/05
DA  - 2018/05
TI  - The Principle and Application of Deep Learning Algorithm
BT  - Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
PB  - Atlantis Press
SP  - 835
EP  - 838
SN  - 1951-6851
UR  - https://doi.org/10.2991/ncce-18.2018.138
DO  - 10.2991/ncce-18.2018.138
ID  - Hu2018/05
ER  -