Sciweavers

2 search results - page 1 / 1
» Penalized least squares, model selection, convex hull classe...
Sort
View
ESANN
2001
13 years 6 months ago
Penalized least squares, model selection, convex hull classes and neural nets
We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...
Gerald H. L. Cheang, Andrew R. Barron
IJCNN
2007
IEEE
13 years 11 months ago
Agnostic Learning versus Prior Knowledge in the Design of Kernel Machines
Abstract— The optimal model parameters of a kernel machine are typically given by the solution of a convex optimisation problem with a single global optimum. Obtaining the best p...
Gavin C. Cawley, Nicola L. C. Talbot