Inductive Learning of Categories from Examples Using Minimum Cost Representations
Proceedings of the Sixth International Joint Conference on Artificial Intelligence. .
Abstract
The problem of learning categories from a sequence of examples is considered in terms of maintaining a minimum-cost representation for the s et of categories. Categori es here are subse ts of a set of natural numbers. Computational aspects of the following problems are addr essed: (1) how are the category represent a tions updated as an incremental change is made to o ne catego ry, (2) how can a minimum cost representation for a new category be obtained in terms of existi ng ones? and (3) how does the enlargement of the known univers e of objects affec t representations of known ca te g ories? We then discuss extensions of our methodology to domains whi c h in c lude structure in the c ategori cal descripti o ns .
@inproceedings{ijcai1979p191,
title = {Inductive Learning of Categories from Examples Using Minimum Cost Representations},
author = {Tanimoto, Steven L.},
booktitle = {Proceedings of the Sixth International Joint Conference on
Artificial Intelligence, {IJCAI-79}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Bruce G. Buchanan},
year = {1979},
month = {8},
url = {https://ijcai.org/proceedings/1979/191},
}
TY - CPAPER TI - Inductive Learning of Categories from Examples Using Minimum Cost Representations AU - Tanimoto, Steven L. T2 - Proceedings of the Sixth International Joint Conference on Artificial Intelligence, IJCAI-79 PB - International Joint Conferences on Artificial Intelligence PY - 1979 UR - https://ijcai.org/proceedings/1979/191 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
