Abstract
The application of neural networks is continuously increasing as the research interests in neural networks advance. Despite the experience accumulated, practitioners constantly face the obstacle of network design which is application dependent. There have been numerous attempts to automate the network design process. A popular approach uses evolutionary computing technique such as genetic algorithms (GAs) and has been successfully applied to design a wide range of network architecture. However, there are a few drawbacks such as high computational cast and incomprehensible network evolution. This paper presents a neural network design algorithm based on a classifier system which is enhanced with a hill climbing strategy to perform efficient search through the solution space. The proposed algorithm has been successfully used to design networks for two benchmark problems, namely XOR function learning and two spiral separation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Robbins, G., Plumbley, M. D., Hughes, J. C., Fallside, F., and Prager, R., 1993, Generation and adaptation of neural networks by evolutionary techniques (GANNET), Neural Computing and Applications, 1(1):23–31.
Schaffer, J. D., Whitley, D., and Eshelman, L. J., 1992, Combinations of genetic algorithms and neural networks: A survey of the state of the art, in Whitley, L. D. and Schaffer, J. D., editors, Proceedings of International Workshop on Combinations of Genetic Algorithms and Neural Networks, 1–37, IEEE Computer Society Press.
Tsui, K. C. and Plumbley, M., 1995, An empirical study of two approaches to automated pRAM network design, in Proceedings of the J 995 International Symposium on Artificial Neural Networks, C1.17–24.
Tsui, K. C. and Plumbley, M., 1997, A genetic-based adaptive hillclimber, To appear in the 5th European Congress on Intelligent Techniques and Soft Computing.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J., 1986, Learning internal representation by error propagation, in Rumelhart, D. E. and McClelland, J. L., editors, Parallel Distributed Processing, volume I, chapter 8, 318–362, MIT Press.
Holland, J. H., 1992, Adaptation in Natural and Artificial Systems; MIT Press, 2nd edition.
Miller, G. F. and Todd, P. M., 1989, Designing neural networks using genetic algorithms, in Schaffer, J. D., editor, Proceedings of the Third International Conference on Genetic Algorithms, 379–384, Morgan Kaufmann: San Mateo, Calif.
Beale, R. and Jackson, T., editors, 1990, Neural Computing: An Introduction, Adam Hilger.
Lang, K. J. and Witbrock, M. J., 1988, Learning to tell two spirals apart, in Touretzky, D. S., Hinton, G., and Sejnowski, T., editors, Proceedings of the 1988 Connectionist Models Summer School. Morgan Kaufmann: San Mateo.
Chua, H. C., Jia, J., Chen, L., and Gong, Y., 1995, Solving two-spiral problem through input data encoding, Electronics Letters, 31(10):813–814.
Cios, K. J. and Liu, N., 1992, A máchine learning method for generation of a neural network architecture: A continuous ID3 algorithm, IEEE Trans. Neural Networks, 3(2):280–291.
Klagges, H. and Soegtrop, M., Limited fan-in random wired cascade-correlation, Anonymous ftp from ftp.cis.ohio-state.edu:/pub/neuroprose.
Koza, J. R., 1992, A genetic approach to the truck backer upper problem and the inter-twined spiral problem, in Proceedings of the International Joint Conference on Neural Networks, 311–318.
Waterhouse, S. R. and Robinson, A. J., 1994, Classification using hierarchical mixtures of experts, in IEEE Workshop on Neural Networks for Signal Processing, 177–186.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag London
About this paper
Cite this paper
Tsui, K.C., Plumbley, M. (1998). Designing Neural Networks using a Genetic Rule-based System. In: Chawdhry, P.K., Roy, R., Pant, R.K. (eds) Soft Computing in Engineering Design and Manufacturing. Springer, London. https://doi.org/10.1007/978-1-4471-0427-8_8
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0427-8_8
Publisher Name: Springer, London
Print ISBN: 978-3-540-76214-0
Online ISBN: 978-1-4471-0427-8
eBook Packages: Springer Book Archive