Affiliation:
1. Nanjing University of Posts and Telecommunications
Abstract
Traditional algorithms of training neural networks have some weakness. A new approach using weight function neural networks was proposed in recent years, which overcomes the shortcomings of traditional neural networks. This paper takes Padé approximation as weight functions and we get the method of how to find the Padé weight functions with given samples. Then complexity is also analysed in detailed in this paper. Finally simulation experiments are done to verify the results.
Publisher
Trans Tech Publications, Ltd.
Reference7 articles.
1. Daiyuan Zhang. Neural Network New Theory and Method [M]. Beijing: Tsinghua University Press, (2006).
2. Yi Ding, Qi Feng. A modular neural network architecture with concept [J]. Neurocomputing, 2014, 125( 11): 3-6.
3. Daiyuan Zhang. A new kind of algorithm in Spline weight function neural network [J]. Systems Engineering and Electronics, 2006, 28(9): 1434-1446.
4. Yu Yao. Research of Padé weight function neural network and the optimal routing algorithm[D]. Nanjing: NJUPT, (2010).
5. Paul Sablonnière. B-splines and Hermite-Padé approximants to the exponential function[J]. Journal of Computational and Applied Mathematics, 2008, 219( 2): 509-517.