DMCA
Growing radial basis neural networks: Merging supervised and unsupervised learning with network growth techniques (1997)
| Venue: | IEEE Transactions on Neural Networks |
| Citations: | 58 - 3 self |
BibTeX
@ARTICLE{Karayiannis97growingradial,
author = {Nicolaos B. Karayiannis and Glenn Weiqun Mi},
title = {Growing radial basis neural networks: Merging supervised and unsupervised learning with network growth techniques},
journal = {IEEE Transactions on Neural Networks},
year = {1997},
volume = {8},
pages = {1492--1506}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract—This paper proposes a framework for constructing and training radial basis function (RBF) neural networks. The proposed growing radial basis function (GRBF) network begins with a small number of prototypes, which determine the locations of radial basis functions. In the process of training, the GRBF network grows by splitting one of the prototypes at each growing cycle. Two splitting criteria are proposed to determine which prototype to split in each growing cycle. The proposed hybrid learning scheme provides a framework for incorporating existing algorithms in the training of GRBF networks. These include unsupervised algorithms for clustering and learning vector quantization, as well as learning algorithms for training single-layer linear neural networks. A supervised learning scheme based on the minimization of the localized class-conditional variance is also proposed and tested. GRBF neural networks are evaluated and tested on a variety of data sets with very satisfactory results. Index Terms — Class-conditional variance, network growing, radial basis neural network, radial basis function, splitting criterion,
Keyphrases
radial basis neural network radial basis function network growth technique single-layer linear neural network splitting criterion vector quantization grbf network network growing supervised learning scheme data set satisfactory result grbf neural network grbf network grows localized class-conditional variance index term class-conditional variance small number neural network unsupervised algorithm
