Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
Artificial Intelligence
Artificial Intelligence
Machine Learning
Version spaces without boundary sets
AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
Hi-index | 0.00 |
Instance retraction is a difficult problem for concept learning by version spaces. In this paper, two new version-space representations are introduced: instance-based maximal boundary sets and instance-based minimal boundary sets. They are correct representations for the class of admissible concept languages and are efficiently computable. Compared to other representations, they are the most efficient practical version-space representations for instance retraction.