1164 search results - page 11 / 233 » A Model Selection Approach for Local Learning |
NECO
2002
13 years 7 months ago
2002
We present a novel approach to dealing with overfitting in black-box models. It is based on the leverages of the samples, i.e. on the influence that each observation has on the pa...
PKDD
2009
Springer
14 years 2 months ago
2009
Springer
Abstract. Feature selection in reinforcement learning (RL), i.e. choosing basis functions such that useful approximations of the unkown value function can be obtained, is one of th...
NECO
1998
13 years 7 months ago
1998
We introduce a constructive, incremental learning system for regression problems that models data by means of spatially localized linear models. In contrast to other approaches, t...
ICML
2004
IEEE
14 years 27 days ago
2004
IEEE
The paper is concerned with two-class active learning. While the common approach for collecting data in active learning is to select samples close to the classification boundary,...
PAMI
2006
13 years 7 months ago
2006
We present a Bayesian method for mixture model training that simultaneously treats the feature selection and the model selection problem. The method is based on the integration of ...