3038 search results - page 221 / 608 » High-Speed Function Approximation |
160
click to vote
ESANN
2006
15 years 8 months ago
2006
We focus on neuro-dynamic programming methods to learn state-action value functions and outline some of the inherent problems to be faced, when performing reinforcement learning in...
173
click to vote
ESANN
2001
15 years 7 months ago
2001
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...
166
click to vote
DMTCS
2003
15 years 7 months ago
2003
Let h : N → Q be a computable function. A real number x is h-monotonically computable (h-mc, for short) if there is a computable sequence (xs) of rational numbers which converges...
136
click to vote
AMC
2010
15 years 6 months ago
2010
The paper deals with the numerical solution of inverse Sturm-Liouville problems with unknown potential symmetric over the interval [0, ]. The proposed method is based on the use o...
177
click to vote
FUIN
2006
15 years 6 months ago
2006
In this paper we derive the bounds for Validation (known also as Hold-Out Estimate and Train-and-Test Method). We present the best possible bound in the case of 0-1 valued loss fun...