Abstract
A new algorithm using rational weight functions for training neural networks is proposed in this paper. Distinct from the constant weights obtained by traditional learning algorithms (such as BP, RBF algorithms and so on), the new algorithm finds rational weight functions using reciprocal differences with simple network’s topology by two layers. The process of how to get the rational weight function networks from the sample interpolation points is given. The results of numerical simulation show that the rational weight functions can find some useful information inherent in the source of data, and the new algorithm has high approximation accuracy, high learning speed and good performance of generalization.
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
Zhang, D.: New theories and methods on neural networks. Tsinghua university press, Beijing (2006)
Zhang, D.: New algorithm for training feedforward neural networks with cubic spline weight functions. Jounal of Systhms Engineering and Electronics 28, 1434–1437 (2006) (in Chinese)
Zhang, D.: New algorithm for training neural networks based on generalized Чебышев polynomials. Jounal of Systhms Engineering and Electronics 30, 2274–2279 (2008) (in Chinese)
Zhang, D.: Training algorithm for veural networks based on distributed parallel calculation. Jounal of Systhms Engineering and Electronics 32, 386–391 (2010) (in Chinese)
Rumelhart, D.E., McClelland, J.L.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1. MIT Press, Cambridge (1986)
Hagan, M.T., Demuth, H.B., Beale, M.: Neural Network Design. China Machine Press, Beijing (2002)
Ampazis, N., Perantonis, S.J.: Two highly efficient second order algorithms for training feedforward networks. IEEE Transactions on Neural Networks 13, 1064–1073 (2002)
Cortes, C., Vapnic, V.: Support Vector Networks. Machine Learning 20, 273–297 (1995)
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
Zhang, D. (2011). Training Neural Networks by Rational Weight Functions. In: Deng, H., Miao, D., Lei, J., Wang, F.L. (eds) Artificial Intelligence and Computational Intelligence. AICI 2011. Lecture Notes in Computer Science(), vol 7004. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23896-3_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-23896-3_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23895-6
Online ISBN: 978-3-642-23896-3
eBook Packages: Computer ScienceComputer Science (R0)