Call for Papers
The Twentieth International Conference on Machine Learning
Washington, DC USA
August 21-24, 2003
The Twentieth International Conference on Machine Learning (ICML-2003)
will be held in Washington D.C. August 21-24, 2003. The conference
will bring together researchers to exchange ideas and report recent
progress in the field of machine learning.
---------------------
Topics for Submission
---------------------
ICML-2003 welcomes submissions on all topics related to machine learning.
We specifically encourage papers on the following topics:
- Applications of machine learning, particularly those that require
non-standard techniques or shed light on limitations of existing
techniques.
- The role of learning in design and configuration, logical and
spatial reasoning, motor control, and more generally on learning for
performance tasks carried out by intelligent agents.
- The discovery of scientific laws and taxonomies, the construction of
componential and structural models, and learning at multiple levels
of temporal and spatial resolution.
- Computational models of human learning, exploratory research that
describes novel learning tasks, work that integrates familiar
methods to demonstrate new functionality, and agent architectures in
which learning plays a central role.
- The effect of the developers' decisions about problem formulation,
representation, data quality, and reward function on the learning
process.
- Empirical studies that combine natural data (to show relevance) with
synthetic data (to understand conditions on behavior), along with
formal analyses that make contact with empirical results, especially
where the aim is to identify sources of power, rather than to show
one method is superior to others.
We also welcome submissions from all traditional topics of machine
learning. Submissions that demonstrate both theoretical and empirical
rigor are especially encouraged.
------------------------
Format of the Conference
------------------------
The conference will include one day of workshops and tutorials and
three days of technical presentations, poster sessions and informal
gatherings designed to foster discussion of research in machine learning.
The conference will include both plenary and parallel tracks for the
presentation of papers published in the conference proceedings.
Speakers will also present their work at an evening poster session,
which will allow conference attendees to discuss the work with the
authors at greater length. In addition to paper presentations, there
will be talks given by several invited speakers.
The conference will be co-located with KDD-2003 and COLT-2003.
Details of the co-location will be announced shortly.
-----------------
Paper Submission
-----------------
Authors should submit papers using the same format and length as will
be required for the final proceedings version. Detailed instructions,
as well as templates for LaTeX and Word will soon be available.
The deadline for submission to ICML-2003 is Friday, February 14,
2003. Submission will be entirely electronic.
ICML-2003 allows simultaneous submission to other conferences,
provided this fact is clearly indicated on the submission form.
Accepted papers will appear in the conference proceedings only if they
are withdrawn from other conferences. Simultaneous submissions that
are not clearly specified as such will be rejected.
--------------
Review Process
--------------
All papers submitted to ICML-2003 will be read by at least two
reviewers, as well as an area chair. We will continue the policy of
conditionally accepting papers that are not publishable in their
initial form, but that the reviewers feel can be improved enough in
time to appear in the proceedings. If a paper is conditionally
accepted, the requirements for acceptance will be explicitly listed on
the review form. Papers that have been conditionally accepted will be
reviewed again after re-submission.
---------------
Important Dates
---------------
Abstracts due: February 10, 2003
Submissions due: February 14, 2003
Acceptance decisions mailed to authors: April 25, 2003
Camera-ready copies of all accepted papers due: May 16, 2003
Authors of conditionally accepted
papers notified: May 23, 2003
--------------
Program Chairs
--------------
Tom Fawcett, Hewlett-Packard Labs
Nina Mishra, Hewlett-Packard Labs and Stanford University
--------------
Area Chairs
--------------
David Aha Case-based Reasoning, Instance-based Learning
Shai Ben-David Computational Learning Theory, Multi-task
Learning, Support Vector Machines
Rich Caruana Multi-Task Learning/Inductive Transfer,
Learning to Rank/Order Data,Feature
Selection, Ensemble Methods
Mark Craven Computational Biology, Information
Extraction, Rule Learning
Johannes Gehrke Decision Tree/Rule Induction, Learning
From/With Data Streams
Haym Hirsh Applications, Information Retrieval, Learning
with Labeled/Unlabeled data, Text Classification
David Jensen Relational learning, Applications, Evaluation of
Learning Processes
Eamonn Keogh Temporal/multimedia data,
Clustering/Unsupervised Learning,
Computational Biology, Time Series Data
John Lafferty Information retrieval, Ensemble methods,
Markov Methods, Learning with
Labeled/Unlabeled Data
Pat Langley Scientific Discovery, Planning, Adaptive
Interfaces, Vision
Stan Matwin Natural Language, Inductive Logic
Programming, Text Classification, Relational
Learning
Dan Oblinger Meta-Learning/Learning Behavior,
Computational Biology
Michael Pazzani Applications, Cognitive Modeling,
Cost-Sensitive Learning, Decision Tree/Rule
Induction
Dan Roth Computational Learning Theory, Natural
Language, On-line Learning
Mehran Sahami Text Classification, Feature Selection,
Clustering/Unsupervised Learning
Dale Schuurmans Ensemble Methods, Bayesian Networks,
Markov Methods, Reinforcement Learning
John Shawe-Taylor Computational Learning Theory, Support
Vector Machines, Connectionist Learning
Satinder Singh Reinforcement Learning, Multi-agent
learning, Markov methods, Connectionist
learning
Peter Stone Multi-agent Learning, Reinforcement
Learning, Robotics
David Stork Bayesian Networks, Clustering/Unsupervised
Learning, Connectionist Learning
----------------------
Additional Information
----------------------
For additional information, please see the conference web site:
http://www.hpl.hp.com/conferences/icml2003
which will provide additional details as they become available.
If you have questions about ICML-2003, please send electronic mail to
Tom Fawcett and Nina Mishra at [EMAIL PROTECTED]
