Title :
THINK: a system of classification rules
Author :
MouraPires, F. ; SteigerGarcao, A.
Author_Institution :
Fac. de Ciencias e Tecnologia, Univ. Nova de Lisboa
Abstract :
A formalism to describe the problem of learning by example is proposed, and an algorithm for rule-based classification is presented. The notions of `known,´ `dc´ (don´t care) and `unknown´ rules are introduced, and the differences between them are described. Canonical, elementary and essential rules are explained. Two different processes for finding the elementary rules starting from the canonical rules are demonstrated
Keywords :
knowledge based systems; learning systems; THINK; classification rules; don´t care; known; learning by example; rule-based classification; unknown; Classification algorithms; Classification tree analysis; Decision trees; Expert systems; Knowledge acquisition; Learning systems; Machine learning; Machine learning algorithms; Multidimensional systems; Proposals;
Conference_Titel :
Intelligent Control, 1990. Proceedings., 5th IEEE International Symposium on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-8186-2108-7
DOI :
10.1109/ISIC.1990.128496
