CFP

			   Call for Papers
ECML Workshop: Machine Learning as Experimental Philosophy of Science
	     2001 European Conference on Machine Learning
		 Freiburg, Germany, 3 September 2001
----------------------------------------------------------------------

Machine learning studies inductive strategies in algorithms.  The
philosophy of science investigates inductive strategies as they appear
in scientific practice. Although the two disciplines have developed
largely independently, they share many of the same issues.  This is
slowly coming to be recognized in a number of ways, as evidenced in
the annual Uncertainty in AI and AI and Statistics conferences.  This
workshop will explore the extent to which the methods and resources of
philosophy of science and machine learning can inform one another.

In "Computational Philosophy of Science" (1988) Paul Thagard presented
a challenge to the philosophical community: philosophical theories of
scientific method, if they are worth their salt, should be
implementable as computer programs.  In this workshop we will address
this challenge and also the inverse challenge to machine learning
researchers: both machine learning algorithms and methods for
evaluating machine learning algorithms should be implementations of
sensible approaches to philosophy of science.  Machine learning
researchers have only recently discovered the relevance of statistics
and philosophical views on the foundations of statistics to evaluating
the performance of their systems; we hope this workshop will carry
that discussion further.

The workshop will therefore focus on such questions as:

  1. Can machine learning experiments tell us about inductive discovery in
science?

  2. What theoretical results in computational learning can be useful
in understanding scientific methods?  How can accounts of scientific
confirmation, explanation, discovery and consilience be used to
develop automatic learning systems?

  3. How can we assess induction? What statistical or other criteria
need to be met to prefer one machine learning algorithm and/or
scientific method over another? What is the role in machine learning
and science of model building versus prediction?

  4. Is there a substantial difference between scientific reasoning as
conceived in the philosophy of science and in machine learning?

  5. Is scientific method indeed mechanizable? Are scientific
practices algorithmic?

Note: ECML will be co-located with PKDD 2001 -- the European Conference
on the Principles and Practices of Knowledge Discovery in Databases.
For more details see:
http://www.informatik.uni-freiburg.de/~ml/ecmlpkdd/

++++++++++++++++
Invited Speakers
++++++++++++++++

Professor Kevin Kelly (CMU, Philosophy), author of "The Logic of
Reliable Inquiry (Oxford, 1996).  His recent work concerns reliable
belief revision, the solution of methodological regresses, and
efficient convergence.

Dr Peter Flach (Bristol, Computer Science), co-editor of "Abduction
and Induction: essays on their relation and integration" (Kluwer,
2000) and co-organiser of workshops on Abductive and Inductive
Reasoning in AI at ECAI'96, IJCAI'97 and ECAI'98.

++++++++++++++++
Important Dates:
++++++++++++++++

Papers due:					 8 June 2001
Notification:					29 June 2001
Camera-ready due:				13 July 2001
Workshop:					 3 Sept 2001

+++++++++++++++++++++++
Submission Instructions
+++++++++++++++++++++++

We prefer papers to be submitted electronically in a postscript email
attachment to both organizers simultaneously (i.e., to
hilanb@cs.bris.ac.uk and korb@csse.monash.edu.au).

++++++++++++++++++++
Workshop Organizers:
++++++++++++++++++++

Hilan Bensusan (University of Bristol) hilanb@cs.bris.ac.uk
Kevin Korb (Monash University) korb@csse.monash.edu.au