From Black and White to Full Colour: Extending Redescription Mining Outside the Boolean World

Talk announcement:
HIIT Seminar Kumpula, Friday March 11 10:15, Exactum C222

SPEAKER:
Esther Galbrun
University of Helsinki

TITLE:
From Black and White to Full Colour: 
Extending Redescription Mining Outside the Boolean World

ABSTRACT:
Redescription mining is a powerful data analysis tool that is used to
find multiple descriptions of the same entities.  However, current
redescription mining methods cannot handle other than Boolean data,
this makes discretization a prerequisite, entailing a possibly harmful
loss of information.  We extend redescription mining to real-valued
data using a surprisingly simple and efficient approach and give an
example of application, for an important task in biology known as
niche-finding.

Redescription mining is a powerful data analysis tool that is used to find 
multiple descriptions of the same entities.  The current redescription 
mining methods cannot handle other than Boolean data, making 
discretization a prerequisite when using non-Boolean data.

We extend redescription mining to real-valued data using a surprisingly 
simple and efficient approach. We demonstrate our algorithm with a 
real-world task of niche-finding, an important problem in biology.

Joint work with Pauli Miettinen


Welcome!
--Matti Järvisalo