Nonlinear Function Learning Using Radial Basis Function Networks: Convergence and Rates

Authors:
Adam Krzyżak;Dominik Schäfer
Affiliations:
Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada H3G 1M8 and Institute of Control Engineering, Technical University of Szczecin, Szczecin, Poland 70- ...;Department of Mathematcs, Stuttgart University, Stuttgart, Germany D-70569
Venue:
ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Year:
2006

Citing 16
Cited 0

Multilayer feedforward networks are universal approximators

Neural Networks
Probabilistic neural networks

Neural Networks
Universal approximation using radial-basis-function networks

Neural Computation
Approximation and radial-basis-function networks

Neural Computation
Decision theoretic generalizations of the PAC model for neural net and other learning applications

Information and Computation
On radial basis function nets and kernel regression: statistical consistency, convergence rates, and receptive field size

Neural Networks
Approximation and Estimation Bounds for Artificial Neural Networks

Machine Learning - Special issue on computational learning theory
Regularization theory and neural networks architectures

Neural Computation
Pattern Recognition and Neural Networks

Pattern Recognition and Neural Networks
Learning in Neural Networks: Theoretical Foundations

Learning in Neural Networks: Theoretical Foundations
Estimation of Dependences Based on Empirical Data: Empirical Inference Science (Information Science and Statistics)

Estimation of Dependences Based on Empirical Data: Empirical Inference Science (Information Science and Statistics)
Fast learning in networks of locally-tuned processing units

Neural Computation
Nonparametric regression estimation by normalized radial basis function networks

IEEE Transactions on Information Theory
Nonparametric estimation via empirical risk minimization

IEEE Transactions on Information Theory
Nonparametric estimation and classification using radial basis function nets and empirical risk minimization

IEEE Transactions on Neural Networks
Radial basis function networks and complexity regularization in function learning

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We apply normalized RBF networks to the problem of learning nonlinear regression functions. The parameters of the networks are learned by empirical risk minimization and complexity regularization. We study convergence of the RBF networks for various radial kernels as the number of training samples increases. The rates of convergence are also examined.