Abstract
The determination of the optimal architecture of a supervised neural network is an important and a difficult task. The classical neural network topology optimization methods select weight(s) or unit(s) from the architecture in order to give a high performance of a learning algorithm. However, all existing topology optimization methods do not guarantee to obtain the optimal solution. In this work, we propose a hybrid approach which combines variable selection method and classical optimization method in order to improve optimization topology solution. The proposed approach suggests to identify the relevant subset of variables which gives a good classification performance in the first step and then to apply a classical topology optimization method to eliminate unnecessary hidden units or weights. A comparison of our approach to classical techniques for architecture optimization is given.
An erratum to this chapter can be found at http://dx.doi.org/10.1007/11550907_163 .
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bishop, C.M.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995)
Reed, R.: Pruning algorithms — A survey. IEEE Transactions on Neural Networks 4, 740–746 (1993)
John, G.H., Kohavi, R., Pfleger, K.: Irrelevant features and the subset selection problem. In: International Conference on Machine Learning, Journal version in AIJ , pp. 121–129 (1994), available at http://citeseer.nj.nec.com/13663.html
Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artificial Intelligence 97, 273–324 (1997)
Blum, A., Langley, P.: Selection of relevant features and examples in machine learning. Artificial Intelligence 97, 245–271 (1997)
Le Cun, Y., Denker, J.S., Solla, S.A.: Optimal brain damage. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems: Proceedings of the 1989 Conference, pp. 598–605. Morgan Kaufmann, San Mateo (1990)
Hassibi, B., Stork, D.G.: Second order derivatives for network pruning: Optimal brain surgeon. In: Hanson, S.J., Cowan, J.D., Giles, C.L. (eds.) Advances in Neural Information Processing Systems, vol. 5, pp. 164–171. Morgan Kaufmann, San Mateo (1993)
Hassibi, B., Stork, D.G., Wolff, G.: Optimal brain surgeon: Extensions and performance comparison. In: Cowan, J.D., Tesauro, G., Alspector, J. (eds.) Advances in Neural Information Processing Systems, vol. 6, pp. 263–270. Morgan Kaufmann Publishers, Inc., San Francisco (1994)
Stahlberger, A., Riedmiller, M.: Fast network pruning and feature extraction by using the unit-OBS algorithm. In: Mozer, M.C., Jordan, M.I., Petsche, T. (eds.) Advances in Neural Information Processing Systems, vol. 9, p. 655. The MIT Press, Cambridge (1997)
Attik, M., Bougrain, L., Alexandre, F.: Optimal brain surgeon variants for feature selection. In: International Joint Conference on Neural Networks - IJCNN 2004, Budapest, Hungary (2004)
Attik, M., Bougrain, L., Alexandre, F.: Optimal brain surgeon variants for optimization. In: 16h European Conference on Artificial Intelligence - ECAI 2004, Valencia, Spain (2004)
Thrun, S.B., Bala, J., Bloedorn, E., Bratko, I., Cestnik, B., Cheng, J., Jong, K.D., Džeroski, S., Fahlman, S.E., Fisher, D., Hamann, R., Kaufman, K., Keller, S., Kononenko, I., Kreuziger, J., Michalski, R.S., Mitchell, T., Pachowicz, P., Reich, Y., Vafaie, H., de Welde, W.V., Wenzel, W., Wnek, J., Zhang, J.: The MONK’s problems: A performance comparison of different learning algorithms. Technical Report CS-91-197, Carnegie Mellon University, Pittsburgh, PA (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Attik, M., Bougrain, L., Alexandre, F. (2005). Neural Network Topology Optimization. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3697. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550907_9
Download citation
DOI: https://doi.org/10.1007/11550907_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28755-1
Online ISBN: 978-3-540-28756-8
eBook Packages: Computer ScienceComputer Science (R0)