On Intrinsic Complexity of Learning Geometrical Concepts from Texts
No Thumbnail Available
Date
1999-06-01T00:00:00Z
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The goal of this paper is to quantify complexity of algorithmic learning of geometrical concepts from growing finite segments. The geometrical concepts we consider are variants of open-hulls. We use intrinsic complexity as our complexity measure. The scale we use is based on a hierarchy of degrees of intrinsic complexity composed of simple natural ground degrees such as INIT and COINIT.