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)
]