Nonparametric regression estimation by normalized radial basis function networks

This paper establishes weak and strong universal consistency of regression estimates based on normalized radial basis function networks when the network parameters are chosen by empirical risk minimization.

Saved in:
Bibliographic Details
Published in:IEEE transactions on information theory 2005-03, Vol.51 (3), p.1003-1010
Main Authors: Krzyzak, A., Schafer, D.
Format: Article
Language:English
Subjects:
Applied sciences
Consistency
Covering numbers
Detection, estimation, filtering, equalization, prediction
Eigenvalues and eigenfunctions
Empirical analysis
empirical risk minimization
Estimates
Exact sciences and technology
Information, signal and communications theory
Interpolation
Kernel
Minimization
Multilayer perceptrons
Networks
Neural networks
nonparametric regression estimation
normalized radial basis function networks
Optimization
Parameter estimation
Radial basis function
Radial basis function networks
Regression
Regression analysis
Risk management
Signal and communications theory
Signal, noise
Smoothing methods
Telecommunications and information theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper establishes weak and strong universal consistency of regression estimates based on normalized radial basis function networks when the network parameters are chosen by empirical risk minimization.
ISSN:0018-9448
1557-9654
DOI:10.1109/TIT.2004.842632