A Modified Back Propagation Algorithm of Neural Network with Global Optimization

Article Preview

Abstract:

The advantages and weakens of traditional BP algorithm is briefly analyzed and an efficient global optimization algorithm is proposed.The basic principle of the algorithm is presented,and a new BP neural network algorithm based on the existing BP algorithm and the new global optimization algorithm is proposed, considering the new global optimization algorithm can solve the problem of local minimum efficiently. To verify the effectiveness of the new BP algorithm,the paper compared the experimental results of various algorithms in solving function fitting problem.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

232-238

Citation:

Online since:

October 2014

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2014 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

[1] X.P. Qiu, N. Tao, Y. Tan, X.X. Wu, Constructing of the risk classification model of cervical cancer by artificial neural network, Expert Systems with Applications, vol. 32(4), May, 2007, pp.1094-1099, doi: 10. 1016/j. eswa. 2006. 02. 020.

DOI: 10.1016/j.eswa.2006.02.020

Google Scholar

[2] Z. Chen and S. Jagannathan, Generalized Hamilton-Jacobi-Bellman Formulation-Based Neural Network Control of Affine Nonlinear Discrete-Time Systems, IEEE Trans. On Neural Networks, vol. 19(1), Jan. 2008, pp.90-106, doi: 10. 1109/TNN. 2007. 900227.

DOI: 10.1109/tnn.2007.900227

Google Scholar

[3] M. A. Mazurowski, P. A. Habas, J. M. Zurada, J. Y. Lo, J. A. Baker and G. D. Tourassi, Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance, Neural Networks, vol. 21(2-3), Mar-Apr. 2008, pp.427-436.

DOI: 10.1016/j.neunet.2007.12.031

Google Scholar

[4] M. Chen, T. Gautama and D. P. Mandic, An Assessment of Qualitative Performance of Machine Learning Architectures: Modular Feedback Networks, IEEE Trans. On Neural Networks, vol. 19(1), Jan. 2008, pp.183-189, doi: 10. 1109/TNN. 2007. 902728.

DOI: 10.1109/tnn.2007.902728

Google Scholar

[5] K. Zou, S. Liu and L. Xu, New fuzzy BP neural network algorithm and its application in stock market, International Conference on Computational Intelligence and Software Engineering, vol. 1, pp.51-55, (2009).

DOI: 10.1109/cise.2009.5365011

Google Scholar

[6] Xiaoyuan, L., Bin, Q., and Lu, W. (2009).

Google Scholar

[7] W. Jin Z.J. Li L.S. Wei H. Zhen The Improvements Of BP Neural Network Learning Algorithm, 5th International Conference on Signal Processing Proceedings, 2000. WCCC-ICSP 2000, Publication Date: 21-25 August 2000 Volume: 3, p.1647 – 1649.

DOI: 10.1109/icosp.2000.893417

Google Scholar

[8] Zou M Y, Zou X. Global Optimization: An Auxiliary Cost Function Approach[J]. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 2000, 30(3): 347-354.

DOI: 10.1109/3468.844358

Google Scholar