Concept Learning and the Problem of Small Disjuncts
Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Machine Learning. Pages 813-817.
Abstract
Ideally, definitions induced from examples should consist of all, and only, disjuncts that are meaningful (e .g., as measured by a statistical significance test) and have a low error rate. Existing inductive systems create definitions that are ideal with regard to large disjuncts, but far from ideal with regard to small disjuncts, where a small (large) disjunct is one that correctly classifies few (many) training examples. The problem with small disjuncts is that many of them have high rates of misclassification and it is difficult to eliminate the errorprone s~all disjuncts from a definition without adversely affecting other disjuncts in the definition. Various approaches to this problem are e valuated , including the novel approach of using a bias different than the "maximum generality" bias. This approach, and some others , prove partly successful, but the problem of small disjuncts remains open.
@inproceedings{ijcai1989p130,
title = {Concept Learning and the Problem of Small Disjuncts},
author = {Holte, Robert C. and Acker, Liane and Porter, Bruce W.},
booktitle = {Proceedings of the Eleventh International Joint Conference on
Artificial Intelligence, {IJCAI-89}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {N. S. Sridharan},
pages = {813--817},
year = {1989},
month = {8},
note = {Machine Learning},
url = {https://ijcai.org/proceedings/1989/130},
}
TY - CPAPER TI - Concept Learning and the Problem of Small Disjuncts AU - Holte, Robert C. AU - Acker, Liane AU - Porter, Bruce W. T2 - Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, IJCAI-89 PB - International Joint Conferences on Artificial Intelligence PY - 1989 SP - 813 EP - 817 UR - https://ijcai.org/proceedings/1989/130 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
