Orthogonal RBF Neural Network Approximation

Authors:
Péter András
Affiliations:
Department of Mathematics & Computer Science, Babes-Bolyai University, Cluj, Romania. e-mail: peter@civitas.org.soroscj.ro
Venue:
Neural Processing Letters
Year:
1999

Citing 6
Cited 2

Multilayer feedforward networks are universal approximators

Neural Networks
Universal approximation using radial-basis-function networks

Neural Computation
Approximation and Estimation Bounds for Artificial Neural Networks

Machine Learning - Special issue on computational learning theory
An integral representation of functions using three-layered networks and their approximation bounds

Neural Networks
Estimates of the number of hidden units and variation with respect to half-spaces

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation

On the variability of neural network classification measures in the protein secondary structure prediction problem

Applied Computational Intelligence and Soft Computing
On the variability of neural network classification measures in the protein secondary structure prediction problem

Applied Computational Intelligence and Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The approximation properties of the RBF neural networks are investigated in this paper. A new approach is proposed, which is based on approximations with orthogonal combinations of functions. An orthogonalization framework is presented for the Gaussian basis functions. It is shown how to use this framework to design efficient neural networks. Using this method we can estimate the necessary number of the hidden nodes, and we can evaluate how appropriate the use of the Gaussian RBF networks is for the approximation of a given function.