1227 search results - page 148 / 246 » Learning Rates for Q-Learning |
ICML
2007
IEEE
15 years 10 months ago
2007
IEEE
Intuitively, learning should be easier when the data points lie on a low-dimensional submanifold of the input space. Recently there has been a growing interest in algorithms that ...
ICML
2008
IEEE
15 years 10 months ago
2008
IEEE
We consider the least-square linear regression problem with regularization by the 1-norm, a problem usually referred to as the Lasso. In this paper, we present a detailed asymptot...
ICML
2004
IEEE
15 years 10 months ago
2004
IEEE
We propose to study links between three important classification algorithms: Perceptrons, Multi-Layer Perceptrons (MLPs) and Support Vector Machines (SVMs). We first study ways to...
ALT
2005
Springer
15 years 6 months ago
2005
Springer
Abstract. We propose an independence criterion based on the eigenspectrum of covariance operators in reproducing kernel Hilbert spaces (RKHSs), consisting of an empirical estimate ...
ICDM
2009
IEEE
15 years 4 months ago
2009
IEEE
— In a data-mining approach, a model for estimation of Aerosol Optical Depth (AOD) from satellite observations is learned using collocated satellite and groundbased observations....