Learning Logic Programs Using Definite Equality Theories as Background Knowledge

Akihiro YAMAMOTO

Learning Logic Programs Using Definite Equality Theories as Background Knowledge

Akihiro YAMAMOTO

Full Text Views

0

Cite this

Summary :

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.

Publication: IEICE TRANSACTIONS on Information Vol.E78-D No.5 pp.539-544

Publication Date: 1995/05/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Algorithmic Learning Theory)

Category: Computational Learning Theory

Cite this

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 -