A MATLAB-Based Study on Approximation Performances of Improved Algorithms of Typical BP Neural Networks

Shuo Ding; Qing Hui Wu

doi:10.4028/www.scientific.net/AMM.313-314.1353

Paper Titles

Technology Development and New Issues of Distribution Automation in Smart Grid
p.1331

On the Simplification of Data Based on Standard MODBUS Protocol
p.1337

Design of Network Adapter Compatible OCP for High-Throughput NOC
p.1341

The Application of Global Forecast Function in the Power System Load Forecasting Software Development
p.1347

A MATLAB-Based Study on Approximation Performances of Improved Algorithms of Typical BP Neural Networks
p.1353

The Future Manufacturing System and Cloud Computing
p.1357

Design and Implementation of Hybrid Micro Energy Harvester for Autonomous WSN Components
p.1362

Design of Software for High-Speed Inkjet-Printing System Based on Distributed
p.1367

Research of FPGA Based LXI Bus Clock Synchronization Technology
p.1371

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 313-314A MATLAB-Based Study on Approximation Performances...

A MATLAB-Based Study on Approximation Performances of Improved Algorithms of Typical BP Neural Networks

Abstract:

BP neural networks are widely used and the algorithms are various. This paper studies the advantages and disadvantages of improved algorithms of five typical BP networks, based on artificial neural network theories. First, the learning processes of improved algorithms of the five typical BP networks are elaborated on mathematically. Then a specific network is designed on the platform of MATLAB 7.0 to conduct approximation test for a given nonlinear function. At last, a comparison is made between the training speeds and memory consumption of the five BP networks. The simulation results indicate that for small scaled and medium scaled networks, LM optimization algorithm has the best approximation ability, followed by Quasi-Newton algorithm, conjugate gradient method, resilient BP algorithm, adaptive learning rate algorithm. Keywords: BP neural network; Improved algorithm; Function approximation; MATLAB

You might also be interested in these eBooks

Machinery Electronics and Control Engineering II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 313-314)

Pages:

1353-1356

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.313-314.1353

Citation:

Cite this paper

Online since:

March 2013

Authors:

Shuo Ding, Qing Hui Wu

Keywords:

BP Neural Network (BPNN), Function Approximation, Improved Algorithm, MATLAB

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

References

[1] Rong Xie,Xinmin Wang,Yan Li and Kairui Zhao. Research and Application on Improved BP Neural Network Algorithm, 2010 5th IEEE Conference on Industrial Electronics and Application, Vol. 3 (2010), pp.1462-1466

DOI: 10.1109/iciea.2010.5514820

Google Scholar

[2] SU Gao-Li,DENG Fang-Ping. On the Improving Backpropagation Algorithms of the Neural Networks Based on MATLAB Language[J].Bulletin of Science and Technology, Vol. 19 (2003), pp.130-135. (in Chinese)

Google Scholar

[3] MoIIer M F. A scaled conjugate gradient algorithm for fast supervised Learning［J］. Neural Networks，Vol.6(1993), pp.525-533

DOI: 10.1016/s0893-6080(05)80056-5

Google Scholar