Abstract
We propose an evolutionary method for the design of Beta basis function neural networks (BBFNN). Classical training algorithms start with a predetermined network structure for neural networks. Generally speaking the neural network is either insufficient or over-complicated. This paper describes a hierarchical genetic learning model of the BBFNN. In order to examine the performance of the proposed algorithm, it is used for functional approximation problem. The results obtained have been encouraging.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Alimi, A.M. Hassine, R. and Selmi, M Beta Fuzzy Logic Systems: Approximation Properties in the SISO Case, Int. J. Applied Mathematics and Computer Science, Special issue edited by D. Rutkowska and L.A. Zadeh, vol. 10, no. 4, pp. 101–119, (2000).
Alimi, A.M. The Beta Fuzzy System: Approximation of Standard Membership Functions Proc. 17eme Journees Tunisiennes d’Electrotechnique et d’Automatique: JTEA’97, Nabeul, Tunisia, Nov., vol. 1, pp. 108–112, (1997).
Aouiti, C. Alimi, A. M. and Maalej, A. A Hierarchical Genetic Algorithm for the Design of Beta Basis Function Neural Network”, Proceedings of the International Joint Conference on Neural Networks, IJCNN ’02, Volume: 2, pp. 1246–1251, (2002).
Aouiti, C. Alimi, A. M. and Maalej, A. A Genetic Designed Beta Basis Function Neural Network for Approximating Multi- Variables Functions, in V. Kurkova et al. (eds.) Artificial Neural Nets and Genetic Algorithms, Springer-Verlag, Wien, pp. 383–386 (2001).
Billings,S. A. and Zheng,G. L. Radial Basis Function Network Configuration Using Genetic Algorithms, Neural Networks, Vol. 8, No. 6, pp. 877–890, (1995).
Goldberg, D.E. Genetic Algorithms in Search, Optimization, and Machine Learning, Reading, MA: Addison-Wesley (1989).
Musavi, M.T., Ahmed, W., Chan, K.H, Faris, B.K. and Hummels, D.M. On the training of radial basis function classifiers, Neural Networks, Vol. 5, pp. 595–603, (1992).
Muhlenbein, H. and Schlierkamp, V. D. Predictive models for the breeder genetic algorithm, Evolutionary Computation, 1(1), (1993).
Rahmouni, A. and Benmohamed, M. Genetic Algorithm Based Methodology to Generate Automatically Optimal Fuzzy Systems, IEE Proc-Control Theory Appl., Vol. 145, No. 6 pp. 583–586, (1998).
Rosenblatt, F. Representation of Functions by superpositions of a Step or Sigmoidal Function and their Applications to Neural Network Theory, Project PARA, Cornell Aeronautical Lab. Rep., No. 85: 640–1, Buffalo, NY (1957).
Samuel, P. and Gisele, L. A Genetic Algorithm for Designing Distributed Computer Network Topologies, IEEE Trans. Systems, Man, and Cybernetics-Part B: Cybernetics, Vol. 28, No. 2, pp. 249–258, (1998).
Yao, X. Evolving Artificial Neural Networks Proceeding of the IEEE, 87, 9, September, 1423–1447 (1999).
Yao X. and Liu, Y. A New Evolutionary System for Evolving Artificial Neural Networks IEEE Transactions on Neural Networks, 8, 3, (1997).
Anderson, T. Rimer M. and Martinez, T. Optimal Artificial Neural Network Architecture Selection for Bagging Proceedings of the International Joint Conference on Neural Networks, IJCNN ’01, Volume: 2, pp. 790 795, (2001).
Demuth, H. and Beale, M. Neural Network Toolbox, For Use with MATLAB User’s Guide, version 3.0., by The MathWorks, Inc. (1998).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Wien
About this paper
Cite this paper
Aouiti, C., Alimi, A.M., Maalej, A. (2003). The Design of Beta Basis Function Neural Network Using Hierarchical Genetic Algorithm. In: Pearson, D.W., Steele, N.C., Albrecht, R.F. (eds) Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-0646-4_39
Download citation
DOI: https://doi.org/10.1007/978-3-7091-0646-4_39
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-00743-3
Online ISBN: 978-3-7091-0646-4
eBook Packages: Springer Book Archive