Abstract
In view of the high complexity of pruning algorithm for OBS (optimal brain surgery) process and the deficiency of its match usage with training algorithm, this paper presents a penalty OBS computational model, in which the pruning condition is considered as a penalty term integrated in the objective function of NN (neural network). Based on its theoretical convergence, this model is realized by adopting the conjugate gradient method. Moreover, the effectiveness of this model is validated by a simulation test. The parallelization of network training process and OBS process ensures the accuracy and the efficiency of regularization so as to improve the generalization capacity of NN.
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
Nong, S., Yantao, X.: Feature Selection Based on Neuro-Fuzzy Networks. Pattern Recognition and Artificial Intelligence 06, 739–745 (2006)
Hassibi, B., Stork, D.G., Wolff, G.: Optimal brain surgeon and general network pruning. In: Proceeding of IEEE International Conference on Neural Networks, pp. 293–299 (1993)
Stahlberger, A., Riedmiller, M.: Fast network pruning and feature extraction by removing complete units. In: Advances in Neural Information Processing Systems, vol. 9, pp. 655–661. MIT Press, Cambridge (1997)
Harkin, S.: Neural network (the original book version 2). Mechanical Industry Press, Beijing (2004)
Zuoyong, L., Penglai, H.: BP network learning ability and generalization ability to meet the uncertainty relation. Science in China (E Series) 33(10), 887–895 (2003)
Yaxiang, Y., Yu, W.: Optimization theory and methods, pp. 154–162. Science Press, Beijing (1997)
Zhongping, W., Pusheng, F.: Optimization theory and methods, pp. 186–200. Science Press, Beijing (2002)
Wanfu, Z., Shijun, Z.: Rough set-based neural network structure optimization design. Computer Engineering and Design 28(17), 4210–4212 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wu, C., Li, D., Song, T. (2011). Penalty-Optimal Brain Surgeon Process and Its Optimize Algorithm Based on Conjugate Gradient. In: Qi, L. (eds) Information and Automation. ISIA 2010. Communications in Computer and Information Science, vol 86. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19853-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-19853-3_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19852-6
Online ISBN: 978-3-642-19853-3
eBook Packages: Computer ScienceComputer Science (R0)