A New Method for Constructing Radial Basis Function Neural Networks

DOI

10.2991/iske.2007.182How to use a DOI?

Keywords

Radial basis function neural network, Norm, Training error, Sensitivity

Abstract

Ignoring the samples far away from the training samples, our study team gives a new norm-based derivative process of localized generalization error boundary. Enlightened by the above research, this paper proposes a new method to construct radial basis function neural networks, which minimizes the sum of training error and stochastic sensitivity. Experimental results show that the new method can lead to simple and better network architecture

Copyright

© 2007, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jinyan Sun
AU  - Xizhao Wang
PY  - 2007/10
DA  - 2007/10
TI  - A New Method for Constructing Radial Basis Function Neural Networks
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 1071
EP  - 1076
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.182
DO  - 10.2991/iske.2007.182
ID  - Sun2007/10
ER  -