Indexed Families of Functionals and Gaussian Radial Basis Functions
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.
Cite
Text
Sandberg. "Indexed Families of Functionals and Gaussian Radial Basis Functions." Neural Computation, 2003. doi:10.1162/089976603762552997Markdown
[Sandberg. "Indexed Families of Functionals and Gaussian Radial Basis Functions." Neural Computation, 2003.](https://mlanthology.org/neco/2003/sandberg2003neco-indexed/) doi:10.1162/089976603762552997BibTeX
@article{sandberg2003neco-indexed,
title = {{Indexed Families of Functionals and Gaussian Radial Basis Functions}},
author = {Sandberg, Irwin W.},
journal = {Neural Computation},
year = {2003},
pages = {455-468},
doi = {10.1162/089976603762552997},
volume = {15},
url = {https://mlanthology.org/neco/2003/sandberg2003neco-indexed/}
}