[UAI] AAAI Fall Symposium

From: Mathias Bauer (Mathias.Bauer@dfki.de)
Date: Sat Mar 04 2000 - 11:28:26 PST

  • Next message: Yoshua Bengio: "[UAI] program of workshop on Selecting and Combining Models with Machine Learning Algorithms"

    [Apologies if you receive multiple copies of this.]

                       *** Second Call for Papers ***

                         AAAI Fall Symposium 2000

                        LEARNING HOW TO DO THINGS

                            November 3-5, 2000
                         Cape Cod, Massachusetts

                        www.dfki.de/~bauer/fs2000

    Symposium Topic

    Knowing how to do things is an important category of knowledge
    underlying many kinds of intelligent behavior in artificial
    agents, such as critiquing, advice giving, tutoring,
    collaboration, and delegation. In the current state of the art,
    most of this procedural knowledge is encoded "manually" by a
    single person (or a small team) who needs to be expert in both
    the task domain and the appropriate knowledge representation
    formalisms. This is a serious bottleneck in the development of
    these kinds of systems.

    The focus of this symposium is on how to automate or partially
    automate the acquisition of procedural knowledge, namely, indexed
    collections of what are variously called macros, plans,
    procedures, or recipes for action. The techniques for acquiring
    this knowledge may depend on many variables, including:

       * size of the domain (e.g., number of recipes)
       * amount of input data
       * number of steps in a typical task
       * type of tasks (e.g., analysis vs. synthesis)
       * number of agents involved (e.g., one, two, or many)
       * type of agents involved (e.g., human vs. computer)
       * intended use of the knowledge (e.g., acting, critiquing,
         etc.)
       * degree of supervision (e.g., teaching vs. unsupervised
         learning)
       * level of abstraction (e.g., primitive operations vs. high-
         level goals)
       * degree of initiative (e.g., learning by experimentation
         versus passively)

    Because of this problem diversity, we hope to include
    participants in the workshop from a number of research areas,
    including:

       * programming by demonstration (highly supervised, small
          amount of input data)
       * data mining (unsupervised, large amount of input data)
       * case-based problem solving (cases are like recipes,
          especially if abstracted)
       * machine learning (range of techniques)
       * cognitive and social sciences (e.g., studies of human
          instructional dialogues)
       * instructable agents

    Important Dates

               Submission of position papers: March 29, 2000
               Notification of acceptance: May 5, 2000
               Registration deadline: May 25, 2000
               Submission of final paper versions: August 25, 2000
               Symposium: November 3-5, 2000

    Submission

    Potential participants should submit a short position paper
    (maximum three pages) containing the following four elements:

      1. Primary contact: name, affiliation, postal and email
         addresses, telephone and fax numbers. Invitations to second-
         ary authors will be made only if they are also listed on this
         submission.
      2. Statement and discussion of two or three important research
         questions that could be presented and discussed at the
         workshop.
      3. Statement and discussion of a domain that could serve as a
         shared example for the workshop. Explain how this particular
         domain would help make our discussion more concrete and
         productive.
      4. A short summary of authors' relevant work, including
         references (please supply URLs if available).

    Please email submissions (plain ascii text only) to
    learninghow@dfki.de. Confirmation of receipt will be returned by
    email.

    Organizing Committee

    Mathias Bauer, DFKI (bauer@dfki.de, co-chair)
    Charles Rich, Mitsubishi Electric Research Lab. (rich@merl.com, co-chair)
    Andrew Garland, Brandeis University
    Abigail Gertner, University Pittsburgh
    Eric Horvitz, Microsoft Research
    Tessa Lau, University Washington
    Neal Lesh, Mitsubishi Electric Research Lab.
    James Lester, North Carolina State University
    Henry Lieberman, MIT
    Jeff Rickel, USC/ISI
    Candace Sidner, Lotus Development Corp.



    This archive was generated by hypermail 2b29 : Sat Mar 04 2000 - 11:35:26 PST