Title :
Radial Basis Function Networks with optimal kernels
Author_Institution :
Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada H3G 1M8
fDate :
7/1/2011 12:00:00 AM
Abstract :
We consider nonlinear function estimation using Radial Basis Function Networks. We analytically determine the optimal radial kernel minimizing the Mean Integrated Square Error (MISE) and the optimal MISE rate of convergence. The rates of convergence for various classes of nonlinear functions and input densities are also considered.
Keywords :
"Kernel","Convergence","Radial basis function networks","Estimation","Approximation methods","Fourier transforms"
Conference_Titel :
Information Theory Proceedings (ISIT), 2011 IEEE International Symposium on
Print_ISBN :
978-1-4577-0596-0
Electronic_ISBN :
2157-8117
DOI :
10.1109/ISIT.2011.6034259
