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.
ICML-2003 welcomes submissions on all topics related to machine learning. In addition to the topics that traditionally are represented at machine learning conferences, we specifically encourage papers on the following topics:
Applications of machine learning, particularly:
exploratory research that describes novel learning tasks;
applications that require non-standard techniques or shed light on limitations of existing learning techniques; and
work that investigates the effect of the developers' decisions about problem formulation, representation or data quality on the learning process.
Analysis of learning algorithms that demonstrate generalization ability and also lead to better understanding of the computational complexity of learning.
The role of learning in spatial reasoning, motor control, and more generally in the performance of intelligent autonomous agents.
The discovery of scientific laws and taxonomies, and the induction of structured models from data.
Computational models of human learning.
Novel formulations of and insights into data clustering.
Learning from non-static data sources: incremental induction, on-line learning and learning from data streams.
Submissions that demonstrate both theoretical and empirical rigor are especially encouraged.
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 presentations of refereed papers, the conference will include talks 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.
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 21, 2003. The submission process 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.
To submit your paper, please go to http://icml.stanford.edu/papers/submit. You will be guided through the submission process. Once you submit a paper you will be given a username and password, with which you may revise the information (including submitting a revised version of the paper) up until the deadline.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.
THERE IS NO LONGER A SEPARATE ABSTRACT
SUBMISSION STEP.
You DO NOT NEED to submit your ABSTRACT in advance.
All papers are due on the 21st.
|
Submissions due |
February 21, 2003 |
|
Acceptance decisions mailed to authors |
May 2, 2003 |
|
Camera-ready copies of all accepted papers due |
May 23, 2003 |
|
Authors of conditionally accepted papers notified |
May 30, 2003 |
Additional information will be posted here as it become available.
If you have questions about ICML-2003, please send email to Tom Fawcett and Nina Mishra at icml2003@hpl.hp.com.
|
Please direct comments and questions about this web page to
tom_fawcett@hp.com
|