Inductive Inference on the Base of Fixed Point Theory
Proceedings of the Tenth International Joint Conference on Artificial Intelligence. Reasoning. Pages 932-937.
Abstract
Inductive reasoning is an important way to generate knowledge from the propositions reflecting facts or directly from data We intend to extract new knowleO;Je in the form of definitions given as fixed point equations. An appropriate fixed point theory is outlined in favour of our aim . This theory suooests the so called generative fixed point equation system as the form of hypothesis thet we are looking for . The defining formulas in these equations use only bounded quantifiers but the relation to be defined may also negetively occur . An inductive inference method is presented es to find the hypothetical equation system from the increasing set of experimental data such that its solutions would fit all the information.
@inproceedings{ijcai1987p192,
title = {Inductive Inference on the Base of Fixed Point Theory},
author = {Gergely, Tamás and Szabó, Zoltán},
booktitle = {Proceedings of the Tenth International Joint Conference on
Artificial Intelligence, {IJCAI-87}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {John McDermott},
pages = {932--937},
year = {1987},
note = {Reasoning},
url = {https://ijcai.org/proceedings/1987/192},
}
TY - CPAPER TI - Inductive Inference on the Base of Fixed Point Theory AU - Gergely, Tamás AU - Szabó, Zoltán T2 - Proceedings of the Tenth International Joint Conference on Artificial Intelligence, IJCAI-87 PB - International Joint Conferences on Artificial Intelligence PY - 1987 SP - 932 EP - 937 UR - https://ijcai.org/proceedings/1987/192 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
