Deadline for submissions: 12 April 1999.

Important Dates | Submission Procedure | Topics
Organizing Committee | Proceedings

Registration and Questionnaire

Since the beginning of AI, experiments have been used to demonstrate the value and potential of new techniques. While in earlier years, the demonstration of a new technique in a toy-domain was sufficient, the standards for acceptable experiments have significantly changed. In later years, more emphasis was put on "real-world problems" as well as on more stringent evaluations of experiments. At least in part stimulated by Paul Cohen's book "Empirical Methods for AI", recent years have seen a massive increase in the use of statistical techniques to assess the validity of empirical results. However, what issues can and should be addressed by such quantitative approaches is not clear.

This one day workshop will aim at clarifying the role of empirical methods in AI. Attention will be given to the traditional factors found in other empirical sciences (such as the problem of representativity of case studies, the proper use of statistics, etc) as well as to the more traditional objectives in AI research: instead of quantifying the relative performance of certain techniques, we are often interested in the development of new concepts allowing a new and hopefully more adequate understanding of certain issues, such as our own cognitive processes, the nature of the tasks we want to solve, etc. What kind of empirical studies can help us in the development of new concepts and frameworks? To stimulate the discussion in the workshop, it will begin with an invited talk by Paul Cohen, author of "Empirical Methods for AI".

TOPICS of interest include:

• the design of computational experiments and the measurement of algorithm performance.
• the choice of problem sets - benchmark problems, artificially generated problems, etc.
• the role of theoretical models in experiments.
• the role of a conceptual framework for characterising tasks and the scope of the validity of results.
• where are quantitative studies useful and where not?
• what alternative (non-quantitative) systematic approaches do we have?

IMPORTANT DATES

SUBMISSION PROCEDURE

Authors should submit a position paper electronically, either as a Postscript or HTML. In addition, authors should submit an ASCII version of their position paper by email.

To submit your paper, send it's URL to achim@cse.unsw.edu.au

Submission Format: The position paper should describe and justify your view on one or more topics relevant to this workshop. See the list of topics in this announcement. The paper should be reasonably concise, i.e. we expect about 1000 words or will normally suffice, but you may use more if needed. It should state your background and the view on one or more topics relevant to this workshop. The first page of submitted papers should include: title, author names, affiliations, postal addresses, electronic mail addresses, telephone and fax numbers for all authors, and a brief abstract. The number of participants is limited to 30 and only one participant per paper can attend. All participants are expected to contribute to the discussions in the workshop.

ORGANIZING COMMITTEE

PROCEEDINGS

The workshop proceedings are available on-line.

Go here to the complete list of IJCAI-99 workshops.