The IJCAI-01 Workshop on EMPIRICAL METHODS IN ARTIFICIAL INTELLIGENCE August 4, 2001, Seattle, USA Workshop Description ===================== In many areas of AI, experiments are the primary means of demonstrating the value and potential of new techniques. It is widely recognized that appropriate empirical approaches often yield new insights into algorithms and systems, and often lead to new research issues, which may be both of experimental and theoretical nature. Thus empirical methods for analysing and comparing algorithms and systems are of considerable interest to many AI researchers. The workshop will bring together researchers from different areas of AI where empirical methods are used to analyse and evaluate algorithms and systems. Workshop topics will include: ============================== -- the design of computational experiments -- performance criteria for algorithms and systems -- methods for analysing, characterising, and comparing algorithmic performance -- the choice of problem sets - benchmark problems, artificially generated problems, etc. -- the role of theoretical models in experiments -- studies from various fields of AI which exemplify good empirical methodology and its value for obtaining interesting results. The domains of interest will cover constraint satisfaction, knowledge acquisition, machine learning and neural networks, natural language processing, planning, reasoning about knowledge, robotics, satisfiability, search techniques, speech recognition, theorem proving, and vision. Format ======= This one-day workshop will start with an invited talk, followed by survey talks in which leading experts will discuss and compare empirical standards in their domains (rather than present the most recent results of their research). Issues raised by the presentations will then be discussed by all workshop participants. Additionally, we are planning to have 1-2 panels (the topics of these panels will be decided based on the submissions) in which panelists first present their position regarding possibly controversial issues, in a 10 minute exposition. A joint lunch or dinner will provide further opportunities for an informal exchange of experiences and ideas. This workshop on Empirical Methods in Artificial Intelligence will be coordinated with the IJCAI-01 Workshop on ``Stochastic Search Algorithms'' (organised by Holger H. Hoos and Thomas Stuetzle) and the IJCAI-01 Tutorial on Stochastic Search (held by Holger H. Hoos and Thomas Stuetzle). Important Dates ================ -- Submission deadline: February 28, 2001 -- Notification of acceptance: March 29, 2001 -- Camera-ready copy deadline: April 11, 2001 -- Workshop: August 4, 2001 Submission Procedure ===================== We ask authors to submit technical papers or position papers either in Postscript or PDF. Every participant is expected to submit at least a 1-page statement of interest. Technical papers should address one or more of the workshop topics. Position papers should describe and justify your view on one or more topics relevant to this workshop. The paper should be reasonably concise; technical papers should be in the range from 4 to 6 pages in IJCAI or AAAI conference style, position papers should be about 1000 words. Submissions should be printed on 8.5" x 11" or A4 paper with at least 1 inch margins on all sides. The first page of the position paper should include the title, a brief abstract, and author names, affiliations, postal addresses, electronic mail addresses, and telephone and fax numbers. To submit a paper, email it (or a URL pointer to it) to hoos@cs.ubc.ca and stuetzle@informatik.tu-darmstadt.de. The number of participants is limited to 40 participants; participants will be selected based on the submitted position paper. All participants are expected to contribute to the discussions in the workshop. Note that all workshop participants must register for the main IJCAI-01 conference. Cochairs ========= Holger H. Hoos Dept. of Computer Science University of British Columbia Vancouver, BC, V6T 1Z4, Canada Email: hoos@cs.ubc.ca WWW: www.cs.ubc.ca/~hoos Thomas Stuetzle Dept. of Computer Science, Intellectics Group Darmstadt University of Technology D-64283 Darmstadt, Germany Email: stuetzle@informatik.tu-darmstadt.de WWW: www.intellektik.informatik.tu-darmstadt.de/~tom Organisation Committee ======================= Ian Gent, University of St Andrews, United Kingdom Tim Menzies, University of British Columbia, Canada Barbara Smith, University of Leeds, United Kingdom Geoff Sutcliffe, University of Miami, USA Additional Information ======================= http://www.intellektik.informatik.tu-darmstadt.de/~tom/IJCAI01/ijcai2001-empai.html