Supervised Learning Errors by Radial Basis Function Neural Networks and Regularization Networks

There is a gap between the theoretical results of regularization theory and practical suitability of regularization-derived networks (RN). On the other hand, radial basis function networks (RBF) that can be seen as a special case of regularization networks, have a rich selection of learning algorith...

Full description

Saved in:
Bibliographic Details
Main Authors: Neruda, R., Vidnerova, P.
Format: Conference Proceeding
Language:English
Subjects:
Computer errors
Computer science
Conferences
Estimation theory
Function approximation
Kernel
Neural networks
Radial basis function
Radial basis function networks
Regularization
Sampling methods
Supervised learning
Training error
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:There is a gap between the theoretical results of regularization theory and practical suitability of regularization-derived networks (RN). On the other hand, radial basis function networks (RBF) that can be seen as a special case of regularization networks, have a rich selection of learning algorithms. In this work we study a relationship between RN and RBF, and show that theoretical estimates for RN hold for a concrete RBF applied on real-world data.
DOI:10.1109/FGCNS.2008.57