Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

February 1, 2003, Vol. 15, No. 2, Pages 455-468
(doi: 10.1162/089976603762552997)
© 2002 Massachusetts Institute of Technology
Indexed Families of Functionals and Gaussian Radial Basis Functions
Article PDF (131.05 KB)
Abstract

We report on results concerning the capabilities of gaussian radial basis function networks in the setting of inner product spaces that need not be finite dimensional. Specifically, we show that important indexed families of functionals can be uniformly approximated, with the approximation uniform also with respect to the index. Applications are described concerning the classification of signals and the synthesis of reconfigurable classifiers.