Proceedings of the 6th International Conference on Electronic, Mechanical, Information and Management Society

Optimal Structure and Parameters of BP Neural Network for Curve Fitting Problem

Authors
Hongjie Yi, Guangrong Ji, Jinghua Liu, Lin Jia
Corresponding Author
Hongjie Yi
Available Online April 2016.
DOI
https://doi.org/10.2991/emim-16.2016.334How to use a DOI?
Keywords
BP neural network; Optimal structure and parameters; Curve fitting; Learning rate; Momentum
Abstract
BP neural network is wildly used because of its strong nonlinear processing ability, self-learning capability, fault tolerance capability. Therefore, the structure and parameters of artificial neural network determine the performance of neural networks. The performance of a BP neural network is not only affected by the network structure, but also affected by its parameters. In this article we will discuss the learning rate and momentum parameters matching relationship and its impact on network performance. The experimental results show that for the curve fitting problem there will be an optimal structure and parameters for the BP neural network.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
6th International Conference on Electronic, Mechanical, Information and Management Society
Part of series
Advances in Computer Science Research
Publication Date
April 2016
ISBN
978-94-6252-176-6
ISSN
2352-538X
DOI
https://doi.org/10.2991/emim-16.2016.334How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Hongjie Yi
AU  - Guangrong Ji
AU  - Jinghua Liu
AU  - Lin Jia
PY  - 2016/04
DA  - 2016/04
TI  - Optimal Structure and Parameters of BP Neural Network for Curve Fitting Problem
BT  - 6th International Conference on Electronic, Mechanical, Information and Management Society
PB  - Atlantis Press
SP  - 1647
EP  - 1652
SN  - 2352-538X
UR  - https://doi.org/10.2991/emim-16.2016.334
DO  - https://doi.org/10.2991/emim-16.2016.334
ID  - Yi2016/04
ER  -