Function Approximation by Neural Networks

Authors:
Fengjun Li
Affiliations:
School of Mathematics and Computer Science, Ningxia University, Yinchuan, People's Republic of China 750021
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Year:
2008

Citing 9
Cited 0

Layered neural networks with Gaussian hidden units as universal approximations

Neural Computation
Universal approximation using radial-basis-function networks

Neural Computation
Approximation by superposition of sigmoidal and radial basis functions

Advances in Applied Mathematics
Approximation of functions by perceptron networks with bounded number of hidden units

Neural Networks
Universal approximation using feedforward neural networks: a survey of some existing methods, and some new results

Neural Networks
On simultaneous approximations by radial basis function neural networks

Applied Mathematics and Computation
Regularization in the selection of radial basis function centers

Neural Computation
An approximation by neural networkswith a fixed weight

Computers & Mathematics with Applications
Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural networks are widely used to approximating continuous functions. In order to study its approximation ability, we discuss the constructive approximation on the whole real lines by an radial basis function (RBF) neural network with a fixed weight. Using the convolution method, we present a family of RBF neural networks with fixed weights that are able to uniformly approximate continuous functions on a compact interval. Our method of proof is constructive. And this work provides a method for function approximation.