Authors: Christoph Globig, Klaus P. Jantke, Steffen Lange, and Yasubumi Sakakibara.
Email: jantke@dfki.de
Source: New Generation Computing Vol. 15, No. 1, 1997, 59-85.
Abstract.
Case-based reasoning is deemed an important technology to
alleviate the bottleneck of knowledge acquisition in artificial intelligence (AI). In
case-based reasoning, knowledge is represented in the form of particular cases
with an appropriate similarity measure rather than any form of rules. The
case-based reasoning paradigm adopts the view that an AI system is dynamically
changing during its life-cycle which immediately leads to learning
considerations.
Within the present paper, we investigate the problem of case-based learning of
indexable classes of formal languages. Prior to learning considerations, we study
the problem of case-based representability and show that every indexable class is
case-based representable with respect to a fixed similarity measure. Next, we
investigate several models of case-based learning and systematically analyze
their strength as well as their limitations. Finally, the general approach to
case-based learnability of indexable classes of formal languages is prototypically
applied to so-called containment decision lists, since they seem particularly
tailored to case-based knowledge processing.
©Copyright 1998 Ohmsha,Ltd.