Forgetting and Compacting data in Concept Learning
Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence. Cognitive Modelling. Pages 432-437.
Abstract
Incremental concept learning algorithms using backtracking have to store previous data. These data can be ordered by the "is more specific than" relation. Using this order only the most informative data have to be stored, and the less informative data can be discarded. Moreover, under certain conditions some data can be replaced by automatically generated, more informative data. We investigate some conditions for data to be discarded, independently of the chosen concept learning algorithm or concept representation language. Then an algorithm for discarding data is presented in the framework of Iterative Versionspaces, which is a depth-first algorithm computing versionspaces as introduced by Mitchell. We update the datastructures used in the Iterative Versionspaces algorithm, while preserving its most important properties.
@inproceedings{ijcai1995p57,
title = {Forgetting and Compacting data in Concept Learning},
author = {Sablon, Gunther and de Raedt, Luc},
booktitle = {Proceedings of the Fourteenth International Joint Conference on
Artificial Intelligence, {IJCAI-95}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Chris S. Mellish},
pages = {432--437},
year = {1995},
note = {Cognitive Modelling},
url = {https://ijcai.org/proceedings/1995/57},
}
TY - CPAPER TI - Forgetting and Compacting data in Concept Learning AU - Sablon, Gunther AU - de Raedt, Luc T2 - Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, IJCAI-95 PB - International Joint Conferences on Artificial Intelligence PY - 1995 SP - 432 EP - 437 UR - https://ijcai.org/proceedings/1995/57 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
