PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Ensemble Learning with Evolutionary Computation: Application to Feature Ranking
Kees Jong, Elena Marchiori and Michele Sebag
In: PPSN, Parallel Problem Solving from Nature, sept. 2004, Birmingham.


A new ensemble approach for Feature Selection is presented, aggregating the feature rankings extracted from the hypotheses extracted along independent runs with evolutionary learning. A statistical model is devised to enable the direct evaluation of the approach; comparative experimental results show its good behavior on non-linear concepts when the features outnumber the examples.

Postscript - PASCAL Members only - Requires a viewer, such as GhostView
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:608
Deposited By:Michele Sebag
Deposited On:29 December 2004