Advanced Search

Generating and Generalizing Models of Visual Objects

Research and Teaching Output of the MIT Community

Show simple item record Connell, Jonathan H. en_US Brady, Michael en_US 2004-10-01T20:17:30Z 2004-10-01T20:17:30Z 1985-07-01 en_US
dc.identifier.other AIM-823 en_US
dc.description.abstract We report on initial experiments with an implemented learning system whose inputs are images of two-dimensional shapes. The system first builds semantic network descriptions of shapes based on Brady's smoothed local symmetry representation. It learns shape models form them using a substantially modified version of Winston's ANALOGY program. A generalization of Gray coding enables the representation to be extended and also allows a single operation, called ablation, to achieve the effects of many standard induction heuristics. The program can learn disjunctions, and can learn concepts suing only positive examples. We discuss learnability and the pervasive importance of representational hierarchies. en_US
dc.format.extent 24 p. en_US
dc.format.extent 4899583 bytes
dc.format.extent 3834482 bytes
dc.format.mimetype application/postscript
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.relation.ispartofseries AIM-823 en_US
dc.subject vision en_US
dc.subject learning en_US
dc.subject shape description en_US
dc.subject representation of shape en_US
dc.title Generating and Generalizing Models of Visual Objects en_US

Files in this item

Name Size Format Description 4.672Mb Postscript
AIM-823.pdf 3.656Mb PDF

This item appears in the following Collection(s)

Show simple item record