288 pp. per issue
6 x 9, illustrated
2014 Impact factor:

Neural Computation

Summer 1991, Vol. 3, No. 2, Pages 246-257
(doi: 10.1162/neco.1991.3.2.246)
© 1991 Massachusetts Institute of Technology
Universal Approximation Using Radial-Basis-Function Networks
Article PDF (504.73 KB)

There have been several recent studies concerning feedforward networks and the problem of approximating arbitrary functionals of a finite number of real variables. Some of these studies deal with cases in which the hidden-layer nonlinearity is not a sigmoid. This was motivated by successful applications of feedforward networks with nonsigmoidal hidden-layer units.

This paper reports on a related study of radial-basis-function (RBF) networks, and it is proved that RBF networks having one hidden layer are capable of universal approximation. Here the emphasis is on the case of typical RBF networks, and the results show that a certain class of RBF networks with the same smoothing factor in each kernel node is broad enough for universal approximation.