A Global Learning Algorithm for a RBF Network

Authors

Qiuming Zhu, University of Nebraska at OmahaFollow
Yao Cai, University of Nebraska at Omaha
Luzheng Liu, University of Nebraska at Omaha

Document Type

Article

Publication Date

4-1999

Publication Title

Neural Networks

Volume

12

Issue

3

First Page

527

Last Page

540

Abstract

This article presents a new learning algorithm for the construction and training of a RBFneural network. The algorithm is based on a global mechanism of parameter learning using a maximum likelihood classification approach. The resulting neurons in the RBF network partitions a multidimensional pattern space into a set of maximum-size hyper-ellipsoid subspaces in terms of the statistical distributions of the training samples. An important feature of the algorithm is that the learning process includes both the tasks of discovering a suitable network structure and of determining the connection weights. The entire network and its parameters are thought of evolved gradually in the learning process.

Recommended Citation

Zhu, Qiuming; Cai, Yao; and Liu, Luzheng, "A Global Learning Algorithm for a RBF Network" (1999). Computer Science Faculty Publications. 49.
https://digitalcommons.unomaha.edu/compscifacpub/49