A Paper Abstract by Benjamin Grosof

Declarative Bias for Structural Domains (June 29 1989)

by Benjamin N. Grosof and Stuart J. Russell

Abstract: We present a formal solution to the problem of situation identification in learning of structural concepts. Structural concepts are characterized by the interrelationships and attributes of their parts, rather than by just their own direct attributes. Our solution extends the declarative approach to bias of (Russell and Grosof, 1987) by formalizing the beliefs about relevancy in a more complex form that expresses the preservation of properties under mappings, using second-order logic to express the existence of isomorphisms. Concept learning, including prediction, analogical inference and single-instance generalization, then emerges as deduction from such isomorphic determinations plus instance data.
Last update: 1-8-98
Up to Benjamin Grosof's Papers page
Up to Benjamin Grosof home page
[ IBM Research home page ]

[ IBM home page | Order | Search | Contact IBM | Help | (C) | (TM) ]