BIB-VERSION:: CS-TR-v2.0
          ID:: STAN//CS-TR-82-950
       ENTRY:: June 01, 1995
ORGANIZATION:: Stanford University, Department of Computer Science
       TITLE:: Learning physical description from functional definitions,
               examples and precedents
        TYPE:: Technical Report
      AUTHOR:: Winston, Patrick H.
      AUTHOR:: Binford, Thomas O.
      AUTHOR:: Katz, Boris
      AUTHOR:: Lowry, Michael
        DATE:: January 1983
       PAGES:: 28
    ABSTRACT:: It is too hard to tell vision systems what things look like.
               It is easier to talk about purpose and what things are for.
               Consequently, we want vision systems to use functional
               descriptions to identify things, when necessary, and we want
               them to learn physical descriptions for themselves, when
               possible.

               This paper describes a theory that explains how to make such
               systems work. The theory is a synthesis of two sets of ideas:
               ideas about learning from precedents and exercises developed
               at MIT and ideas about physical description developed at
               Stanford. The strength of the synthesis is illustrated by way
               of representative experiments. All of these experiments have
               been performed with an implementation system.
       NOTES:: [Adminitrivia V1/Prg/19950601]
         END:: STAN//CS-TR-82-950