We consider multidimensional shift-invariant input-output maps G from a relatively compact set of functions S to a set of real-valued functions, and we give criteria under which these maps can be uniformly approximated arbitrarily well using a certain structure consisting of a not-necessarily linear
Gaussian radial basis functions and the approximation of input–output maps
✍ Scribed by Irwin W. Sandberg
- Publisher
- John Wiley and Sons
- Year
- 2003
- Tongue
- English
- Weight
- 116 KB
- Volume
- 31
- Category
- Article
- ISSN
- 0098-9886
- DOI
- 10.1002/cta.242
No coin nor oath required. For personal study only.
✦ Synopsis
Abstract
Radial basis functions are of interest in connection with a variety of approximation problems in the neural networks area, and in other areas as well. Here we show that the members of some interesting families of shift‐varying input–output maps, that take a function space into a function space, can be uniformly approximated, over an infinite time or space domain, in a certain special way using Gaussian radial basis functions. Copyright © 2003 John Wiley & Sons, Ltd.
📜 SIMILAR VOLUMES
## Abstract We review recent developments in space mapping techniques for modeling of microwave devices. We present a surrogate modeling methodology that utilizes space mapping combined with radial basis function interpolation. The method has advantages both over the standard space mapping modeling
## Abstract Based on a combination of a radial basis function network (RBFN) and a self‐organizing map (SOM), a time‐series forecasting model is proposed. Traditionally, the positioning of the radial basis centres is a crucial problem for the RBFN. In the proposed model, an SOM is used to construct
## Abstract In this study, traveling wave solutions of the modified regularized long wave (MRLW) equation are simulated by using the meshless method based on collocation with well‐known radial basis functions. The method is tested for three test problems which are single solitary wave motion, inter