Efficient specialization of relational concepts

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

An algorithm is presented for a common induction problem, the specialization of overty general concepts. A concept is too general when it matches a negative example. The particular case addressed here assumes that concepts are represented as conjunctions of positive literals, that specialization is performed by conjoining literals to the overly general concept, and that the resulting specializations are to be as general as possible. Although the problem is NP-hard, there exists an algorithm, based on manipulation of bit vectors, that has provided good performance in practice.

Original languageEnglish (US)
Pages (from-to)99-106
Number of pages8
JournalMachine Learning
Volume4
Issue number1
DOIs
StatePublished - Oct 1989
Externally publishedYes

Fingerprint

Computational complexity

Keywords

  • concept induction
  • specialization
  • version spaces

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence

Cite this

Efficient specialization of relational concepts. / VanLehn, Kurt.

In: Machine Learning, Vol. 4, No. 1, 10.1989, p. 99-106.

Research output: Contribution to journalArticle

@article{a6771857be89474ca83715eb794d9424,
title = "Efficient specialization of relational concepts",
abstract = "An algorithm is presented for a common induction problem, the specialization of overty general concepts. A concept is too general when it matches a negative example. The particular case addressed here assumes that concepts are represented as conjunctions of positive literals, that specialization is performed by conjoining literals to the overly general concept, and that the resulting specializations are to be as general as possible. Although the problem is NP-hard, there exists an algorithm, based on manipulation of bit vectors, that has provided good performance in practice.",
keywords = "concept induction, specialization, version spaces",
author = "Kurt VanLehn",
year = "1989",
month = "10",
doi = "10.1007/BF00114805",
language = "English (US)",
volume = "4",
pages = "99--106",
journal = "Machine Learning",
issn = "0885-6125",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Efficient specialization of relational concepts

AU - VanLehn, Kurt

PY - 1989/10

Y1 - 1989/10

N2 - An algorithm is presented for a common induction problem, the specialization of overty general concepts. A concept is too general when it matches a negative example. The particular case addressed here assumes that concepts are represented as conjunctions of positive literals, that specialization is performed by conjoining literals to the overly general concept, and that the resulting specializations are to be as general as possible. Although the problem is NP-hard, there exists an algorithm, based on manipulation of bit vectors, that has provided good performance in practice.

AB - An algorithm is presented for a common induction problem, the specialization of overty general concepts. A concept is too general when it matches a negative example. The particular case addressed here assumes that concepts are represented as conjunctions of positive literals, that specialization is performed by conjoining literals to the overly general concept, and that the resulting specializations are to be as general as possible. Although the problem is NP-hard, there exists an algorithm, based on manipulation of bit vectors, that has provided good performance in practice.

KW - concept induction

KW - specialization

KW - version spaces

UR - http://www.scopus.com/inward/record.url?scp=34249970988&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34249970988&partnerID=8YFLogxK

U2 - 10.1007/BF00114805

DO - 10.1007/BF00114805

M3 - Article

VL - 4

SP - 99

EP - 106

JO - Machine Learning

JF - Machine Learning

SN - 0885-6125

IS - 1

ER -