Premium
Gaussian radial basis functions and the approximation of input–output maps
Author(s) -
Sandberg Irwin W.
Publication year - 2003
Publication title -
international journal of circuit theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.364
H-Index - 52
eISSN - 1097-007X
pISSN - 0098-9886
DOI - 10.1002/cta.242
Subject(s) - radial basis function , basis (linear algebra) , gaussian , radial basis function network , mathematics , space (punctuation) , basis function , function (biology) , connection (principal bundle) , domain (mathematical analysis) , function space , artificial neural network , topology (electrical circuits) , mathematical analysis , computer science , artificial intelligence , geometry , combinatorics , physics , quantum mechanics , evolutionary biology , biology , operating system
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.