Symposium "From Machine Learning to Data Mining" Monday, June 3, 2002, Leuven, Belgium
	Katholieke Universiteit Leuven Departement Computerwetenschappen

The symposium has been a success. We had 63 participants from Belgium and the Netherlands. The slides of the presentations can be found below.

Some pictures/foto's of June 3, 2002.

A report written by Arno Knobbe.

Symposium "From Machine Learning to Data Mining"

With support from

• FWO scientific network Machine Learning for Data Mining and its Applications
• FWO scientific network Declarative Methods in Computer Science

PhD defence

The announcement of the symposium is also available in text format.

• Program
• Registration
• Roadmap
• Abstracts

Symposium "From Machine Learning to Data Mining"
Monday June 3

PhD defense Wim Van Laer
Monday June 3

16.30 pm	Presentation (this will be in Dutch)
17.15 pm	Questions

The defense is followed by a reception.

Your full name (required) :

Your affiliation (optional) :

I want to register for (please specify) :

• the Symposium (including coffee) : yes no
• the lunch (cost € 10): yes no
• the reception after PhD defense : yes no

A detailed description and a map showing how to get there can be found at the Computer Science webpages. De Molen is building 32 on the map.

• In English
• In Dutch

Inductive databases : a declarative data mining approach

Building and mining the multidimensional HIV data cube

Descriptive data mining: current issues

Is Combining Classifiers Better than Selecting the Best One?

We empirically evaluate several state-of-the-art methods for constructing ensembles of classifiers with stacking and show that they perform (at best) comparably to selecting the best classifier from the ensemble by cross validation. We then propose a new method for stacking, that uses multi-response model trees at the meta-level, and show that it clearly outperforms existing stacking approaches, as well as selecting the best classifier from the ensemble by cross validation.