Header menu link for other important links
A reachability-based complexity measure for case-based reasoners
, Ganesan D.
Published in The AAAI Press
Pages: 341 - 346
Case-Based Reasoning relies on the underlying hypothesis that similar problems have similar solutions. The extent to which this hypothesis holds good has been used by CBR designers as a measure of case base complexity, which in turn gives insights on its generalization ability. Several local and global complexity measures have been proposed in the literature. However, the existing measures rely only on the similarity knowledge to compute complexity. We propose a new complexity measure called Reachability-Based Complexity Measure (RBCM) that goes beyond the similarity knowledge to include the effects of all knowledge containers in the reasoner. The proposed measure is evaluated on several realworld datasets and results suggest that RBCM correlates well with the generalization accuracy of the reasoner. © 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
About the journal
JournalProceedings of the 32nd International Florida Artificial Intelligence Research Society Conference, FLAIRS 2019
PublisherThe AAAI Press
Open AccessNo