Colloquium Computer Science: Frank-Michael Schleif, University of Applied Sciences, Würzburg Germany

Title: Proximity based learning - a metric and non-metric adventure

Abstract:
Efficient data analysis strongly depends on the data representation. Most methods rely on (symmetric) similarity or dissimilarity representations using metric inner products or distances.

This permits the use of powerful mathematical formalisms like kernel or branch-and-bound approaches. Similarities and dissimilarities are however often naturally obtained by non-metric proximity measures which are not easily handled by classical learning algorithms.

The talk provides a comprehensive overview for the field of learning with proximity representation focusing on non-metric similarities.

Algorithmic approaches and different applications are shown.

Colloquium coordinators are Prof.dr. M. Aiello (e-mail : M.Aiello rug.nl ) and Prof.dr. M. Biehl (e-mail: M.Biehl rug.nl )

http://www.rug.nl/research/jbi/news/colloquia/computerscience