Approximation and Radial-Basis-Function Networks
- 1 March 1993
- journal article
- Published by MIT Press in Neural Computation
- Vol. 5 (2) , 305-316
- https://doi.org/10.1162/neco.1993.5.2.305
Abstract
This paper concerns conditions for the approximation offunctions in certain general spaces using radial-basis-functionnetworks. It has been shown in recent papers that certain classesof radial-basis-function networks are broad enough for universalapproximation. In this paper these results are considerablyextended and sharpened.Keywords
This publication has 2 references indexed in Scilit:
- Universal Approximation Using Radial-Basis-Function NetworksNeural Computation, 1991
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991