TDIS : an Algebraic Formalization
Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence. Machine Learning. Pages 1008-1014.
Abstract
In the light of the success of Top-Down Induction Systems (TDIS), the problems to be addressed concern the structure of descriptions and the exploration of strategies. This paper introduces a formal model to describe TDIS, based on the use of lattice theory and, more precisely, on the use of a Galois connection. One of the advantages of this formalization is that it justifies the extensive use of attribute-value representation in the case of classical TDIS and generalizes this representation to products of hierarchical posets. In addition, given that there are many different learning strategies for TDIS, this formal model shows the limitations of classical strategies and offers a general framework in which many other strategies can be expressed.
@inproceedings{ijcai1993p139,
title = {TDIS : an Algebraic Formalization},
author = {Ganascia, Jean-Gabriel},
booktitle = {Proceedings of the Thirteenth International Joint Conference on
Artificial Intelligence, {IJCAI-93}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ruzena Bajcsy},
pages = {1008--1014},
year = {1993},
note = {Machine Learning},
url = {https://ijcai.org/proceedings/1993/139},
}
TY - CPAPER TI - TDIS : an Algebraic Formalization AU - Ganascia, Jean-Gabriel T2 - Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, IJCAI-93 PB - International Joint Conferences on Artificial Intelligence PY - 1993 SP - 1008 EP - 1014 UR - https://ijcai.org/proceedings/1993/139 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
