Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

Winter 1991, Vol. 3, No. 4, Pages 579-588
(doi: 10.1162/neco.1991.3.4.579)
© 1991 Massachusetts Institute of Technology
Improving the Generalization Properties of Radial Basis Function Neural Networks
Article PDF (419.39 KB)
Abstract

An important feature of radial basis function neural networks is the existence of a fast, linear learning algorithm in a network capable of representing complex nonlinear mappings. Satisfactory generalization in these networks requires that the network mapping be sufficiently smooth. We show that a modification to the error functional allows smoothing to be introduced explicitly without significantly affecting the speed of training. A simple example is used to demonstrate the resulting improvement in the generalization properties of the network.