Improving the Generalization Properties of Radial Basis Function Neural Networks
- 1 December 1991
- journal article
- Published by MIT Press in Neural Computation
- Vol. 3 (4) , 579-588
- https://doi.org/10.1162/neco.1991.3.4.579
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.Keywords
This publication has 2 references indexed in Scilit:
- Curvature-Driven Smoothing in Backpropagation Neural NetworksPublished by Springer Nature ,1990
- Interpolation of scattered data: Distance matrices and conditionally positive definite functionsConstructive Approximation, 1986