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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This dataset is publically available at ftp://ftp.ira.uka.de/pub/neuron/proben1.tar.gz.
- 2.
This dataset is publically available at http://ftp.ics.uci.edu/pub/machine-learning-databases/iris/.
References
Stoica, F., Boitor, C.: Using the breeder genetic algorithm to optimize a multiple regression analysis model used in prediction of the mesiodistal width of unerupted teeth. Int. J. Comput. Commun. Control 9, 62–70 (2014)
Heaton, J.: Deep Learning and Neural Networks. CreateSpace Independent Publishing Platform (2015)
Souza, A., Soares, F.: Neural Network Programming with Java. Packt Publishing Ltd. (2016)
Rashid, T.: Make Your Own Neural Network. CreateSpace Independent Publishing Platform (2016)
Jacobson, L., Kanber, B.: Genetic Algorithms in Java Basics. Springer, New York (2015)
Simon, D.: Evolutionary Optimization Algorithms. Wiley, Berlin (2013)
Yu, X.-H., Chen, G.-A.: Efficient backpropagation learning using optimal learning rate and momentum. Neural Netw. 10, 517–527 (1997)
Najim, S., Al-Sharibini, M.: Enhancement neural networks design by general genetic algorithm. Basrah J. Sci. 1, 46–54 (2003)
Al-Fadhly, A.: A study of a neuro-genetic system performance. Department of Computer Science, Ph.D. thesis, University of Basrah (2004)
Prechelt, L.: Proben1: a set of neural network benchmark problems and benchmarking rules (1994)
Engelbrecht, A., Cloete, I.: Selective learning using sensitivity analysis. In: The 1998 IEEE International Joint Conference on Neural Networks, Proceedings of the 1998 IEEE World Congress on Computational Intelligence, Anchorage, Alaska, USA, vol. 2, pp. 1150–1155. IEEE (1998)
Khaudeyer, R.: Hybrid approaches: neuro-fuzzy and geno-neuro-fuzzy hybrid system for solving some classification and functions approximation problems. Department of Computer Science, Ph.D. thesis, University of Basrah (2003)
Swain, M., Kumar Dash, S., Dash, S., Mohapatra, A.: An approach for IRIS plant classification using neural network. Int. J. Soft Comput. (IJSC) 3, 79–89 (2012)
Weihong, Z., Shunqing, X.: Optimization of BP neural network classifier using genetic algorithm. Intell. Comput. Evol. Comput. AISC 180, 599–605 (2013)
Karaboga, D., Gorkemli, B., Ozturk, C., Karaboga, N.: A comprehensive survey: artificial bee colony (ABC) algorithm and applications. Artif. Intell. Rev. 42, 21–57 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Alabbas, M., Jaf, S., Abdullah, AH.M. (2017). Optimize BpNN Using New Breeder Genetic Algorithm. In: Hassanien, A., Shaalan, K., Gaber, T., Azar, A., Tolba, M. (eds) Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2016. AISI 2016. Advances in Intelligent Systems and Computing, vol 533. Springer, Cham. https://doi.org/10.1007/978-3-319-48308-5_36
Download citation
DOI: https://doi.org/10.1007/978-3-319-48308-5_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48307-8
Online ISBN: 978-3-319-48308-5
eBook Packages: EngineeringEngineering (R0)