A Critique of the Valiant Model
Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Machine Learning. Pages 837-841.
Abstract
This paper considers the Valiant framework as it is applied to the task of learning logical concepts from random examp les. It is argued that the current interpretation of this Valiant model departs from common sense and practical experience in a number of ways: it does not allow sample dependent bounds, it uses a worst case rather than an average case analysis, and it does not accommodate preferences about hypotheses. It is claimed that as a result, the current model can produce overlyconservative estimates of confidence and can fail to model the logical induction process as it is often implemented. A Bayesian approach is developed, based on the sample dependent notion of disagreement between consistent hypothes es. This approach seems to overcome the indicated problems.
@inproceedings{ijcai1989p134,
title = {A Critique of the Valiant Model},
author = {Buntine, Wray L.},
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 = {837--841},
year = {1989},
month = {8},
note = {Machine Learning},
url = {https://ijcai.org/proceedings/1989/134},
}
TY - CPAPER TI - A Critique of the Valiant Model AU - Buntine, Wray L. T2 - Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, IJCAI-89 PB - International Joint Conferences on Artificial Intelligence PY - 1989 SP - 837 EP - 841 UR - https://ijcai.org/proceedings/1989/134 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
