In this paper we investigate the learnability of relations in Inductive Logic Programming, by using equality theories as background knowledge. We assume that a hypothesis and an observation are respectively a definite program and a set of ground literals. The targets of our learning algorithm are relations. By using equality theories as background knowledge we introduce tree structure into definite programs. The structure enable us to narrow the search space of hypothesis. We give pairs of a hypothesis language and a knowledge language in order to discuss the learnability of relations from the view point of inductive inference and PAC learning.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Akihiro YAMAMOTO, "Learning Logic Programs Using Definite Equality Theories as Background Knowledge" in IEICE TRANSACTIONS on Information,
vol. E78-D, no. 5, pp. 539-544, May 1995, doi: .
Abstract: In this paper we investigate the learnability of relations in Inductive Logic Programming, by using equality theories as background knowledge. We assume that a hypothesis and an observation are respectively a definite program and a set of ground literals. The targets of our learning algorithm are relations. By using equality theories as background knowledge we introduce tree structure into definite programs. The structure enable us to narrow the search space of hypothesis. We give pairs of a hypothesis language and a knowledge language in order to discuss the learnability of relations from the view point of inductive inference and PAC learning.
URL: https://global.ieice.org/en_transactions/information/10.1587/e78-d_5_539/_p
Copy
@ARTICLE{e78-d_5_539,
author={Akihiro YAMAMOTO, },
journal={IEICE TRANSACTIONS on Information},
title={Learning Logic Programs Using Definite Equality Theories as Background Knowledge},
year={1995},
volume={E78-D},
number={5},
pages={539-544},
abstract={In this paper we investigate the learnability of relations in Inductive Logic Programming, by using equality theories as background knowledge. We assume that a hypothesis and an observation are respectively a definite program and a set of ground literals. The targets of our learning algorithm are relations. By using equality theories as background knowledge we introduce tree structure into definite programs. The structure enable us to narrow the search space of hypothesis. We give pairs of a hypothesis language and a knowledge language in order to discuss the learnability of relations from the view point of inductive inference and PAC learning.},
keywords={},
doi={},
ISSN={},
month={May},}
Copy
TY - JOUR
TI - Learning Logic Programs Using Definite Equality Theories as Background Knowledge
T2 - IEICE TRANSACTIONS on Information
SP - 539
EP - 544
AU - Akihiro YAMAMOTO
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 1995
AB - In this paper we investigate the learnability of relations in Inductive Logic Programming, by using equality theories as background knowledge. We assume that a hypothesis and an observation are respectively a definite program and a set of ground literals. The targets of our learning algorithm are relations. By using equality theories as background knowledge we introduce tree structure into definite programs. The structure enable us to narrow the search space of hypothesis. We give pairs of a hypothesis language and a knowledge language in order to discuss the learnability of relations from the view point of inductive inference and PAC learning.
ER -