In Chapter 6, we present results from an alternative paradigm to compare
classifiers. We investigate the hypothesis that StackingC is more stable than other
ensemble learning schemes, i.e. that its learning curve is at the uppermost level
of all learning curves. Surprisingly, we find that there is no significant difference
between all considered schemes within this paradigm.
In Chapter 7, we show that all ensemble learning systems, including StackingC,
Grading (Seewald & Furnkranz, ¨ 2001) and even Bagging (Breiman, 1996)
can be simulated by Stacking. For this we give functionally equivalent definitions
of most schemes as meta classifiers for Stacking.
In Chapter 6, we present results from an alternative paradigm to compareclassifiers. We investigate the hypothesis that StackingC is more stable than otherensemble learning schemes, i.e. that its learning curve is at the uppermost levelof all learning curves. Surprisingly, we find that there is no significant differencebetween all considered schemes within this paradigm.In Chapter 7, we show that all ensemble learning systems, including StackingC,Grading (Seewald & Furnkranz, ¨ 2001) and even Bagging (Breiman, 1996)can be simulated by Stacking. For this we give functionally equivalent definitionsof most schemes as meta classifiers for Stacking.
การแปล กรุณารอสักครู่..
