Abstract
Generalization problem is a key problem in NN society, which can be grouped into two classes: the generalization problem with unlimited size of training sample and that with limited size of training sample. The generalization problem with limited size of training sample is considered in this paper. Similar to margin maximization criterion in SVM, we propose a margin maximization training algorithm for BP network to further improve the generalization ability of BP network. Experimental results show that the margin maximization training algorithm proposed in this paper does improve the performance of BP network, and shows a comparable performance with SVM.
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
Zhang, X.G.: Introduction to Statistical Learning Theory and Support Vector Machines. Acta Automatic Sinica 26, 32–42 (2000)
Shamos, M.I.: Geometric Complexity. In: Proceedings of the 7th ACM Symposium on the Theory of Computing, Albuquerque, New Mexico, pp. 224–233 (1975)
Wang, Q.R.: A CNN Classification Design with Boundary Patching. Acta Automatic Sinica 12, 415–438 (1988)
Rosin, P.L., Fierens, F.: Improving Neural Network Generalisation. In: Proceedings of International Geoscience and Remote Sensing Symposium, Firenze, Italy, vol. 2, pp. 1255–1257 (1995)
Choi, S.H., Rockett, P.: The Training of Neural Classifiers with Condensed Datasets. IEEE Transactions on Systems, Man, and Cybernetics, Part B 32, 202–206 (2002)
Hara, K., Nakayama, K., Kharaf, A.A.M.: A Training Data Selection in On-Line Training for Multilayer Neural Networks. In: Proceedings of IEEE International Joint Conference on Neural Networks, Anchorage, USA, pp. 2247–2252 (1998)
Ferri, F.J., Albert, J.V., Vidal, E.: Considerations about Sample-size Sensitivity of a Family of Edited Nearest-neighbor Rules. IEEE Transactions on System, Man, Cybernetics, Part B: Cybernetics 29, 667–672 (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Wang, K., Wang, Q. (2007). A Margin Maximization Training Algorithm for BP Network. 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_49
Download citation
DOI: https://doi.org/10.1007/978-3-540-72393-6_49
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)