DocumentCode :
1400562
Title :
Growing radial basis neural networks: merging supervised and unsupervised learning with network growth techniques
Author :
Karayiannis, Nicolaos B. ; Mi, Glenn Weiqun
Author_Institution :
Dept. of Electr. Eng., Houston Univ., TX, USA
Volume :
8
Issue :
6
fYear :
1997
fDate :
11/1/1997 12:00:00 AM
Firstpage :
1492
Lastpage :
1506
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 gross 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
Keywords :
feedforward neural nets; learning (artificial intelligence); minimisation; pattern recognition; vector quantisation; class conditional variance; clustering; growing radial basis neural networks; learning vector quantization; minimization; radial basis function neural networks; splitting criteria; stopped criterion; supervised learning; unsupervised learning; Clustering algorithms; Function approximation; Interpolation; Merging; Neural networks; Prototypes; Radial basis function networks; Surface fitting; Unsupervised learning; Vectors;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/72.641471
Filename :
641471
Link To Document :
بازگشت