Skip to main content

Research Repository

Advanced Search

Optimize BpNN using new breeder genetic algorithm

Alabass, Maytham; Jaf, Sardar; Abdullah, Abdul-Hussein M.; Hassanien, Aboul Ella; Shaalan, Khaled; Gaber, Tarek; Azar, Ahmad Taher; Tolba, Mohamed F.

Authors

Maytham Alabass

Sardar Jaf

Abdul-Hussein M. Abdullah

Aboul Ella Hassanien

Khaled Shaalan

Tarek Gaber

Ahmad Taher Azar

Mohamed F. Tolba



Abstract

In this paper, the ability of genetic algorithms in designing artificial neural network (ANN) is investigated. The multi-layer network (MLN) is taken into account as the ANN structure to be optimized. The idea presented here is to use the genetic algorithms to yield contemporaneously the optimization of: (1) the design of NN architecture in terms of number of hidden layers and of number of neurons in each layer; and (2) the choice of the best parameters (learning rate, momentum term, activation functions, and order of training patterns) for the effective solution of the actual problem to be faced. The back-propagation (BP) algorithm, which is one of the best-known training methods for ANNs, is used. To verify the efficiency of the current scheme, a new version of the breeder genetic algorithm (NBGA) is proposed and used for the automatic synthesis of NN. Finally, several problems of the experiment were taken and the results show that the back-propagation neural network (BpNN) classifier improved the current scheme has higher accuracy of classification and greater gradient of convergence than other classifiers, which have been proposed in the literature.

Citation

Alabass, M., Jaf, S., Abdullah, A.-H. M., Hassanien, A. E., Shaalan, K., Gaber, T., Azar, A. T., & Tolba, M. F. (2016, October). Optimize BpNN using new breeder genetic algorithm. Presented at 2nd International Conference on Advanced Intelligent Systems and Informatics (AISI2016), Cairo, Egypt

Presentation Conference Type Conference Paper (published)
Conference Name 2nd International Conference on Advanced Intelligent Systems and Informatics (AISI2016)
Start Date Oct 24, 2016
End Date Oct 26, 2016
Acceptance Date Jul 31, 2016
Online Publication Date Oct 18, 2016
Publication Date Jan 1, 2017
Deposit Date Aug 22, 2016
Pages 373-382
Series Title Advances in intelligent systems and computing
Series Number 533
Series ISSN 2194-5357,2194-5365
Book Title Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2016.
ISBN 9783319483078
DOI https://doi.org/10.1007/978-3-319-48308-5_36
Public URL https://durham-repository.worktribe.com/output/1151353
Additional Information Conference Dates: 24-26 Oct 2016