Title :
Adaptive regression estimation with multilayer feedforward neural networks
Author :
M. Kohler;A. Krzyzak
Author_Institution :
Fachbereich Math., Stuttgart Univ., Germany
fDate :
6/26/1905 12:00:00 AM
Abstract :
We prove a general bound on the expected L/sub 2/ error of adaptive least squares estimates. By applying it to multilayer feedforward neural network regression function estimates we are able to obtain fast rates of convergence in special classes of regression functions such as additive functions.
Keywords :
"Multi-layer neural network","Neural networks","Feedforward neural networks","Least squares approximation","Neurons","Computer science","Computer errors","Convergence","Statistical distributions","Artificial neural networks"
Conference_Titel :
Information Theory, 2004. ISIT 2004. Proceedings. International Symposium on
Print_ISBN :
0-7803-8280-3
DOI :
10.1109/ISIT.2004.1365504
