Autors:

CiteWeb id: 19910000240

CiteWeb score: 2561

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.

The publication "Universal approximation using radial-basis-function networks" is placed in the Top 10000 of the best publications in CiteWeb. Also in the category Computer Science it is included to the Top 10000. Additionally, the publicaiton "Universal approximation using radial-basis-function networks" is placed in the Top 1000 among other scientific works published in 1991.
Links to full text of the publication: