The New Algorithm of BP Artificial Neural Network

DOI

10.2991/isci-15.2015.157How to use a DOI?

Keywords

Neural network; MATALB simulation; new BP Algorithm

Abstract

Propose a new algorithm based on BP neural network algorithm on existing, which basic principle is choosing a freedom weight, by solving the linear equations to achieve hidden layer, combination freedom weight , then obtain weight is necessary weight. This algorithm hasn’t the traditional method such as the local minimum and the slower rate of convergence in BP neural networks algorithm.

Copyright

© 2015, 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)

TY  - CONF
AU  - Mao Luo
AU  - Shaoyun Song
PY  - 2015/01
DA  - 2015/01
TI  - The New Algorithm of BP Artificial Neural Network
BT  - Proceedings of the 2015 International Symposium on Computers & Informatics
PB  - Atlantis Press
SP  - 1191
EP  - 1197
SN  - 2352-538X
UR  - https://doi.org/10.2991/isci-15.2015.157
DO  - 10.2991/isci-15.2015.157
ID  - Luo2015/01
ER  -