Abstract
This paper presents a new pruning method to determine a nearly optimum multi-layer neural network structure. The aim of the proposed method is to reduce the size of the network by freezing any node that does not actively participate in the training process. A node is not active if it has little or no effect to reduce the error of the network as the training proceeds. Experimental results demonstrate a moderate to nearly significant reduction in the network size and generalization performance. A notable improvement in the network's training time is also observed.
Presently at Azad university, Tabriz, Tehran, Iran
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
Le Cun, Y., J.S. Denker, and S. A. Solla. Optimal brain damage. In D.S. Touretzky, editor, Advances in Neural Information Processing Systems (Denver, 1989) (2), pp. 598–605. Morgan Kaufmann, San Mateo, 1990.
Hassibi, B., and D.G. Stork. Optimal brain surgeon. In S.J. Hanson, J.D. Cowan, and C.L. Giles, editors, Advances in Neural Information Processing Systems (Denver, 1992) (5), pp. 164–171. Morgan Kaufmann, San Mateo, 1993.
Sietsma, J., and R.J.F. Dow. Creating artificial neural networks that generalize. Neural Networks 4(1):67–79, 1991.
Mozer, M.C., and P. Smolensky. Skeletonization: A technique for trimming the fat from a network via relevance assessment. In D.S. Touretzky, editor, Advances in Neural Information Processing Systems (Denver, 1988) (1), pp. 107–115. Morgan Kaufmann, San Mateo, 1989.
Reed, R. Pruning algorithms-a survey,“ IEEE transactions on Neural Networks, 4(5):740–747, September 1993.
Reed, R., and R.J. Marks II. Neural Smithing: Supervised Learning in Feed forward Artificial Neural Networks, The MIT press, Cambridge, Massachusetts, 1999.
Fahlman, S.E., and C. Lebiere. The cascade-correlation architecture. In D.S. Touret-sky, editor, Advances in Neural Information Processing Systems (Denver, 1989) (2), pp. 524–532. Morgan Kaufmann, San Mateo, 1990.
Frean, M. The upstart algorithm: a method for constructing and training feed forward neural networks. Neural Computation 2(2):198–209, 1990.
Mézard, M., and J.P. Nadal. Learning in feed forward layered networks: The tiling algorithm. Journal of physics A 22:2191–2203, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Farzan, A., Ghorbani, A.A. (2001). The Bottom-Up Freezing: An Approach to Neural Engineering. In: Stroulia, E., Matwin, S. (eds) Advances in Artificial Intelligence. Canadian AI 2001. Lecture Notes in Computer Science(), vol 2056. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45153-6_31
Download citation
DOI: https://doi.org/10.1007/3-540-45153-6_31
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42144-3
Online ISBN: 978-3-540-45153-2
eBook Packages: Springer Book Archive