Return to search

Learning Physical Descriptions from Functional Definitions, Examples, and Precedents

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 implemented system.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/5669
Date01 November 1982
CreatorsWinston, Patrick H., Binford, Thomas O., Katz, Boris, Lowry, Michael
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format23 p., 6843086 bytes, 946661 bytes, application/postscript, application/pdf
RelationAIM-679

Page generated in 0.0016 seconds