Learning Physical Descriptions from Functional Definitions, Examples, and Precedents

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/5669

Full metadata record

DC Field	Value	Language
dc.creator	Winston, Patrick H.	-
dc.creator	Binford, Thomas O.	-
dc.creator	Katz, Boris	-
dc.creator	Lowry, Michael	-
dc.date	2004-10-01T20:18:51Z	-
dc.date	2004-10-01T20:18:51Z	-
dc.date	1982-11-01	-
dc.date.accessioned	2013-10-09T02:40:45Z	-
dc.date.available	2013-10-09T02:40:45Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-679	-
dc.identifier	http://hdl.handle.net/1721.1/5669	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	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.	-
dc.format	23 p.	-
dc.format	6843086 bytes	-
dc.format	946661 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-679	-
dc.subject	learning	-
dc.subject	form and function	-
dc.title	Learning Physical Descriptions from Functional Definitions, Examples, and Precedents	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI