Title :
Indexed families of functionals, and Gaussian radial basis functions
Author :
Sandberg, Irwin W.
Author_Institution :
Dept. of Electr. & Comput. Eng., Texas Univ., Austin, TX, USA
Abstract :
In this paper, 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.
Keywords :
approximation theory; functional equations; radial basis function networks; signal classification; Gaussian radial basis functions; indexed functionals families; inner product spaces; product space dimensions; reconfigurable classifier synthesis; signal classification; uniform approximation; Application software; Medical diagnosis; Medical signal detection; Network synthesis; Neural networks; Signal synthesis; Smoothing methods; USA Councils;
Conference_Titel :
Circuits and Systems, 2002. MWSCAS-2002. The 2002 45th Midwest Symposium on
Print_ISBN :
0-7803-7523-8
DOI :
10.1109/MWSCAS.2002.1187187
