This paper proposes a framework to learn concepts from di erent kinds of observations. We de ne a language to describe meta-concepts, that represent the sets of possible concepts ...
Recent research in machine learning has focused on supervised induction for simple classi cation and reinforcement learning for simple reactive behaviors. In the process, the eld ...
We describe a case study in tit(', application of symbolic machinc learning techniques for the discow;ry of linguistic rules and categories. A supervised rule induction algor...
The release of Curriculum 2001 coupled with the increasing importance of the World Wide Web and the changes in pedagogy enabled by new technologies has made the choices about what...
Elizabeth S. Adams, Doug Baldwin, Judith Bishop, J...
The present paper considers the effects of introducing inaccuracies in a learner’s environment in Gold’s learning model of identification in the limit. Three kinds of inaccu...