Issues in stacked generalization
Stacked generalization is a general method of using a high-level model to combine lower-
level models to achieve greater predictive accuracy. In this paper we address two crucial …
level models to achieve greater predictive accuracy. In this paper we address two crucial …
Stacked Generalization: when does it work?
Stacked generalization is a general method of using a high-level model to combine lower-
level models to achieve greater predictive accuracy. In this paper we resolve two crucial …
level models to achieve greater predictive accuracy. In this paper we resolve two crucial …
Bounding the generalization error of convex combinations of classifiers: balancing the dimensionality and the margins
V Koltchinskii, D Panchenko… - The Annals of Applied …, 2003 - projecteuclid.org
A problem of bounding the generalization error of a classifier%\break $ f\in\conv (\mathcal
{H}) $, where $\mathcal {H} $ is a" base" class of functions (classifiers), is considered. This …
{H}) $, where $\mathcal {H} $ is a" base" class of functions (classifiers), is considered. This …
Model combination in the multiple-data-batches scenario
KM Ting, BT Low - Machine Learning: ECML-97: 9th European …, 1997 - Springer
The approach of combining models learned from multiple batches of data provide an
alternative to the common practice of learning one model from all the available data (ie, the …
alternative to the common practice of learning one model from all the available data (ie, the …
Learning and exploitation do not conflict under minimax optimality
C Szepesvári - Machine Learning: ECML-97: 9th European …, 1997 - Springer
We show that adaptive real time dynamic programming extended with the action selection
strategy which chooses the best action according to the latest estimate of the cost function …
strategy which chooses the best action according to the latest estimate of the cost function …
Decision combination based on the characterisation of predictive accuracy
KM Ting - Intelligent Data Analysis, 1997 - content.iospress.com
In this article, we first explore an intrinsic problem that exists in the models induced by
learning algorithms. Regardless of the selected algorithm, search methodology and …
learning algorithms. Regardless of the selected algorithm, search methodology and …
Learning from batched data: Model combination versus data combination
Combining models learned from multiple batches of data provide an alternative to the
common practice of learning one model from all the available data (ie the data combination …
common practice of learning one model from all the available data (ie the data combination …
Theory combination: an alternative to data combination
KM Ting, BT Low - 1996 - researchcommons.waikato.ac.nz
The approach of combining theories learned from multiple batches of data provide an
alternative to the common practice of learning one theory from all the available data (ie, the …
alternative to the common practice of learning one theory from all the available data (ie, the …