The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A Programação Lógica Indutiva (ILP) é um estudo de sistemas de aprendizado de máquina que usam teorias oracionais em lógica de primeira ordem como linguagem de representação. Neste artigo, levantamos os fundamentos teóricos da PLI sob os pontos de vista da Lógica da Descoberta e do Aprendizado de Máquina, e tentamos unificar essas duas visões com o apoio da teoria moderna da Programação em Lógica. Em primeiro lugar, definimos vários métodos de construção de hipóteses em PLI e damos os seus fundamentos teóricos de prova, tratando-os como um procedimento que completa provas incompletas. A seguir, discutimos o projeto de algoritmos de aprendizagem individuais usando esses métodos de construção de hipóteses. Revisamos resultados conhecidos sobre programas lógicos de aprendizagem na teoria de aprendizagem computacional e mostramos que esses algoritmos são exemplos de uma estratégia genérica de aprendizagem com métodos de conclusão de prova.
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.
Copiar
Hiroki ARIMURA, Akihiro YAMAMOTO, "Inductive Logic Programming: From Logic of Discovery to Machine Learning" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 1, pp. 10-18, January 2000, doi: .
Abstract: Inductive Logic Programming (ILP) is a study of machine learning systems that use clausal theories in first-order logic as a representation language. In this paper, we survey theoretical foundations of ILP from the viewpoints of Logic of Discovery and Machine Learning, and try to unify these two views with the support of the modern theory of Logic Programming. Firstly, we define several hypothesis construction methods in ILP and give their proof-theoretic foundations by treating them as a procedure which complets incomplete proofs. Next, we discuss the design of individual learning algorithms using these hypothesis construction methods. We review known results on learning logic programs in computational learning theory, and show that these algorithms are instances of a generic learning strategy with proof completion methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_1_10/_p
Copiar
@ARTICLE{e83-d_1_10,
author={Hiroki ARIMURA, Akihiro YAMAMOTO, },
journal={IEICE TRANSACTIONS on Information},
title={Inductive Logic Programming: From Logic of Discovery to Machine Learning},
year={2000},
volume={E83-D},
number={1},
pages={10-18},
abstract={Inductive Logic Programming (ILP) is a study of machine learning systems that use clausal theories in first-order logic as a representation language. In this paper, we survey theoretical foundations of ILP from the viewpoints of Logic of Discovery and Machine Learning, and try to unify these two views with the support of the modern theory of Logic Programming. Firstly, we define several hypothesis construction methods in ILP and give their proof-theoretic foundations by treating them as a procedure which complets incomplete proofs. Next, we discuss the design of individual learning algorithms using these hypothesis construction methods. We review known results on learning logic programs in computational learning theory, and show that these algorithms are instances of a generic learning strategy with proof completion methods.},
keywords={},
doi={},
ISSN={},
month={January},}
Copiar
TY - JOUR
TI - Inductive Logic Programming: From Logic of Discovery to Machine Learning
T2 - IEICE TRANSACTIONS on Information
SP - 10
EP - 18
AU - Hiroki ARIMURA
AU - Akihiro YAMAMOTO
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2000
AB - Inductive Logic Programming (ILP) is a study of machine learning systems that use clausal theories in first-order logic as a representation language. In this paper, we survey theoretical foundations of ILP from the viewpoints of Logic of Discovery and Machine Learning, and try to unify these two views with the support of the modern theory of Logic Programming. Firstly, we define several hypothesis construction methods in ILP and give their proof-theoretic foundations by treating them as a procedure which complets incomplete proofs. Next, we discuss the design of individual learning algorithms using these hypothesis construction methods. We review known results on learning logic programs in computational learning theory, and show that these algorithms are instances of a generic learning strategy with proof completion methods.
ER -