Abstract
This paper presents a new evolutionary system using genetic algorithm for evolving artificial neural networks (ANNs). Existing genetic algorithms (GAs) for evolving ANNs suffer from the permutation problem. Frequent and abrupt recombination in GAs also have very detrimental effect on the quality of offspring. On the other hand, Evolutionary Programming (EP) does not use recombination operator entirely. Proposed algorithm introduces a recombination operator using graph matching technique to adapt structure of ANNs dynamically and to avoid permutation problem. The complete algorithm is designed to avoid frequent recombination and reduce behavioral disruption between parents and offspring. The evolutionary system is implemented and applied to three medical diagnosis problems - breast cancer, diabetes and thyroid. The experimental results show that the system can dynamically evolve compact structures of ANNs, showing competitiveness in performance.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Storn, R., Price, K.: Differential Evolution -a Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces. Technical Report TR-95-012, ICSI (March 1995), ftp.icsi.berkeley.edu
Hancock, P.J.B.: Genetic Algorithms and Permutation Problems: A Comparison of Recombination Operators for Neural Net Structure Specification. In: Proc. COGANN Workshop, Baltimore, MD, pp. 108–122 (1992)
Holland, J.H.: Adaptation in Natural and Artificial Systems. Univ. Michigan Press, Ann Arbor (1975)
Fogel, L., Owens, A., Walsh, M. (eds.): Artificial Intelligence Through Simulated Evolution. Wiley, New York (1966)
Fogel, D.B.: Phenotypes, Genotypes, and Operators in Evolutionary Computation. In: Proc. 1995 IEEE Int. Conf. Evolutionary Computation, Piscataway, NJ, pp. 193–198 (1995)
Yao, X., Liu, Y.: A New Evolutionary System for Evolving Artificial Neural Networks. IEEE Trans. Neural Networks 8(3), 694–713 (1997)
Schalkoff, R.J.: Pattern Recognition: Statistical, Structural and Neural Approaches. John Wiley & Sons, New York (1992)
Busygin, S.: A New Trust Region Technique for the Maximum Weight Clique Problem. Discrete Applied Mathematics (International Symposium on Combinatorial Optimization CO’02) 154(15), 2080–2096 (2006)
Prechelt, L.: Proben1-A Set of Neural Network Benchmark Problems and Benchmarking Rules. Fakultat fur Informatik, Univ. Karlsruhe, Karlsruhe, Germany, Tech. Rep. 21/94 (Sept. 1994)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Mahmood, A., Sharmin, S., Barua, D., Islam, M.M. (2007). Graph Matching Recombination for Evolving Neural Networks. In: Liu, D., Fei, S., Hou, Z., Zhang, H., Sun, C. (eds) Advances in Neural Networks – ISNN 2007. ISNN 2007. Lecture Notes in Computer Science, vol 4492. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72393-6_67
Download citation
DOI: https://doi.org/10.1007/978-3-540-72393-6_67
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72392-9
Online ISBN: 978-3-540-72393-6
eBook Packages: Computer ScienceComputer Science (R0)