Oesterreichisches Forschungsinstitut fuer Artificial Intelligence (OeFAI)
Schottengasse 3, A-1010 Wien
Tel.+43-1-53532810,5336112
-------------------------------------------------------------------------
VORTRAG
*******
Dr.Kai Ming TING
University of Waikato
Hamilton
New Zealand
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.
We resolve two crucial issues which have been considered to be a
`black art' in classification tasks ever since the introduction of
stacked generalization in 1992 by Wolpert: the type of generalizer
that is suitable to derive the higher-level model, and the kind of
attributes that should be used as its input.
We demonstrate the effectiveness of stacked generalization for
combining three different types of learning algorithms.
Zeit: Montag, 28.April 1997, 18:30 Uhr pktl.
Ort: OeFAI, Schottengasse 3, 1010 Wien 1.