The multidimensional function approximation based on constructive wavelet RBF neural network

For the multidimensional continuous function, using constructive feedforward wavelet RBF neural network, we prove that a wavelet RBF neural network with n+1 hidden neurons can interpolate n+1 multidimensional samples with zero error. Then we prove they can uniformly approximate any continuous multidimensional function with arbitrary precision. This method can avoid the defects of conventional neural networks using learning algorithm in practice. The correctness and effectiveness are verified through four numeric experiments.

[1]  Narasimhan Sundararajan,et al.  A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation , 2005, IEEE Transactions on Neural Networks.

[2]  Yang Guo.  Research of Fractional Linear Neural Network and Its Ability for Nonlinear Approach , 2007 .

[3]  Guang-Bin Huang,et al.  Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions , 1998, IEEE Trans. Neural Networks.

[4]  Eduardo D. Sontag,et al.  Feedforward Nets for Interpolation and Classification , 1992, J. Comput. Syst. Sci..

[5]  Lei Chen,et al.  Enhanced random search based incremental extreme learning machine , 2008, Neurocomputing.

[6]  Xuli Han,et al.  Neural Networks for Approximation of Real Functions with the Gaussian Functions , 2007, Third International Conference on Natural Computation (ICNC 2007).

[7]  Zongben Xu,et al.  Simultaneous Lp-approximation order for neural networks , 2005, Neural Networks.

[8]  C. Micchelli.  Interpolation of scattered data: Distance matrices and conditionally positive definite functions , 1986 .

[9]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[10]  F. J. Sainz,et al.  Constructive approximate interpolation by neural networks , 2006 .

[11]  P. Torkzadeh,et al.  Structural optimization with frequency constraints by genetic algorithm using wavelet radial basis function neural network , 2008 .

[12]  Chen Falai.  Applications of Radius Basis Function Neural Networks in Scattered Data Interpolation , 2001 .

[13]  J.I. Mulero-Martinez,et al.  Best Approximation of Gaussian Neural Networks With Nodes Uniformly Spaced , 2008, IEEE Transactions on Neural Networks.

[14]  Xin Li,et al.  Limitations of the approximation capabilities of neural networks with one hidden layer , 1996, Adv. Comput. Math..

[15]  C. Micchelli,et al.  Approximation by superposition of sigmoidal and radial basis functions , 1992 .

[16]  Xuli Han,et al.  Quasi-interpolation for Data Fitting by the Radial Basis Functions , 2008, GMP.

[17]  H. Mhaskar,et al.  Neural networks for localized approximation , 1994 .

[18]  N Mai Duy,et al.  APPROXIMATION OF FUNCTION AND ITS DERIVATIVES USING RADIAL BASIS FUNCTION NETWORKS , 2003 .

[19]  Hou Muzhou,et al.  Constructive approximation to real function by wavelet neural networks , 2008 .

[20]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[21]  Guang-Bin Huang,et al.  Convex incremental extreme learning machine , 2007, Neurocomputing.

[22]  Bernard Delyon,et al.  Accuracy analysis for wavelet approximations , 1995, IEEE Trans. Neural Networks.

[23]  Charles K. Chui,et al.  An Introduction to Wavelets , 1992 .

[24]  Nam Mai-Duy,et al.  Approximation of function and its derivatives using radial basis function networks , 2003 .

[25]  Mauro Maggioni,et al.  Multiscale approximation with hierarchical radial basis functions networks , 2004, IEEE Transactions on Neural Networks.

[26]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[27]  Yu Kai.  Study on performance and application of the wavelet function , 2000 .