Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation

Authors:
Chen-San Chen;Ching-Shiow Tseng
Affiliations:
Department of Mechanical Engineering, Kuang Wu Institute of Technology, Peito, Taipei, Taiwan, 112 R.O.C.;Department of Mechanical Engineering, National Central University, Chungli, Taiwan, 320 R.O.C.
Venue:
International Journal of Intelligent Systems
Year:
2004

Citing 0
Cited 4

Fast and Robust Way of Learning the Fourier Series Neural Networks on the Basis of Multidimensional Discrete Fourier Transform

ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Determining the Weights of A Fourier Series Neural Network on the Basis of the Multidimensional Discrete Fourier Transform

International Journal of Applied Mathematics and Computer Science - Selected Problems of Computer Science and Control
General H∞synchronization of chaotic systems via orthogonal function neural network

ICIC'07 Proceedings of the intelligent computing 3rd international conference on Advanced intelligent computing theories and applications
A method to improve the performance of multilayer perceptron by utilizing various activation functions in the last hidden layer and the least squares method

Neural Processing Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

The orthogonal neural network is a recently developed neural network based on the properties of orthogonal functions. It can avoid the drawbacks of traditional feedforward neural networks such as initial values of weights, number of processing elements, and slow convergence speed. Nevertheless, it needs many processing elements if a small training error is desired. Therefore, numerous data sets are required to train the orthogonal neural network. In the article, a least-squares method is proposed to determine the exact weights by applying limited data sets. By using the Lagrange interpolation method, the desired data sets required to solve for the exact weights can be calculated. An experiment in approximating typical continuous and discrete functions is given. The Chebyshev polynomial is chosen to generate the processing elements of the orthogonal neural network. The experimental results show that the numerical method in determining the weights gives as good performance in approximation error as the known training method and the former has less convergence time. © 2004 Wiley Periodicals, Inc. Int J Int Syst 19: 1257–1275, 2004.