Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising Theories

Abstract. Using domain knowledge in unsupervised learning has shown to be a useful strategy when the set of examples of a given domain has not an evident structure or presents some level of noise. This background knowledge can be expressed as a set of class~fication rules and introduced as a semanti...

Descripción completa

Detalles Bibliográficos
Autores: Béjar, Javier, Cortés, Ulises
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:1998
País:México
Institución:Instituto Politécnico Nacional
Repositorio:Repositorio Digital del IPN
OAI Identifier:oai:www.repositoriodigital.ipn.mx:123456789/14947
Acceso en línea:http://www.repositoriodigital.ipn.mx/handle/123456789/14947
Access Level:acceso abierto
Palabra clave:Keywords. Knowledge Acquisition, Domain Theory, Ill-Structured Domains, Clustering Methods.
id MX_bbd47ef8dcd2b4c573c1be67ab27e33d
oai_identifier_str oai:www.repositoriodigital.ipn.mx:123456789/14947
network_acronym_str MX
network_name_str México
repository_id_str
spelling Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising TheoriesBéjar, JavierCortés, UlisesKeywords. Knowledge Acquisition, Domain Theory, Ill-Structured Domains, Clustering Methods.Abstract. Using domain knowledge in unsupervised learning has shown to be a useful strategy when the set of examples of a given domain has not an evident structure or presents some level of noise. This background knowledge can be expressed as a set of class~fication rules and introduced as a semantic bias during the learning process. In this work we present some experiments on the use of partial domain knowledge with the tool LINNEO+, a conceptual clustering algorithm. The domain knowledge (or domain theory) is used to select a set of examples that will be used to start the learning process, this knowledge has neither to be complete nor consistent. This bias will increase the quality oi the final groups and reduce the effect oi the arder oi the examples. Some measures oi stability 01 class~fication are used. The improvement oi the concepts can be used to enhance and correct the domain knowledge. A set oi heuristics to revise the original domain theory has been experimented, yielding to some interesting results.Instituto Politécnico Nacional - Centro de Investigación en Computación (CIC).Investigación en ComputaciónPDFRevista Computación y Sistemas; Vol. 1 No. 32013-04-09T16:58:13Z2013-04-09T16:58:13Z1998-03-09info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleRevista Computación y Sistemas; Vol. 1 No. 31405-5546http://www.repositoriodigital.ipn.mx/handle/123456789/14947reponame:Repositorio Digital del IPNinstname:Instituto Politécnico Nacionalinstacron:IPNen_USRevista Computación y Sistemas;Vol. 1 No. 3info:eu-repo/semantics/openAccessoai:www.repositoriodigital.ipn.mx:123456789/149472026-02-18T16:44:15Z
dc.title.none.fl_str_mv Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising Theories
title Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising Theories
spellingShingle Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising Theories
Béjar, Javier
Keywords. Knowledge Acquisition, Domain Theory, Ill-Structured Domains, Clustering Methods.
title_short Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising Theories
title_full Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising Theories
title_fullStr Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising Theories
title_full_unstemmed Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising Theories
title_sort Experiments with Domain Knowledge in Unsupervised Learning: U sing and Revising Theories
dc.creator.none.fl_str_mv Béjar, Javier
Cortés, Ulises
author Béjar, Javier
author_facet Béjar, Javier
Cortés, Ulises
author_role author
author2 Cortés, Ulises
author2_role author
dc.subject.none.fl_str_mv Keywords. Knowledge Acquisition, Domain Theory, Ill-Structured Domains, Clustering Methods.
topic Keywords. Knowledge Acquisition, Domain Theory, Ill-Structured Domains, Clustering Methods.
description Abstract. Using domain knowledge in unsupervised learning has shown to be a useful strategy when the set of examples of a given domain has not an evident structure or presents some level of noise. This background knowledge can be expressed as a set of class~fication rules and introduced as a semantic bias during the learning process. In this work we present some experiments on the use of partial domain knowledge with the tool LINNEO+, a conceptual clustering algorithm. The domain knowledge (or domain theory) is used to select a set of examples that will be used to start the learning process, this knowledge has neither to be complete nor consistent. This bias will increase the quality oi the final groups and reduce the effect oi the arder oi the examples. Some measures oi stability 01 class~fication are used. The improvement oi the concepts can be used to enhance and correct the domain knowledge. A set oi heuristics to revise the original domain theory has been experimented, yielding to some interesting results.
publishDate 1998
dc.date.none.fl_str_mv 1998-03-09
2013-04-09T16:58:13Z
2013-04-09T16:58:13Z
dc.type.none.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv Revista Computación y Sistemas; Vol. 1 No. 3
1405-5546
http://www.repositoriodigital.ipn.mx/handle/123456789/14947
identifier_str_mv Revista Computación y Sistemas; Vol. 1 No. 3
1405-5546
url http://www.repositoriodigital.ipn.mx/handle/123456789/14947
dc.language.none.fl_str_mv en_US
language_invalid_str_mv en_US
dc.relation.none.fl_str_mv Revista Computación y Sistemas;Vol. 1 No. 3
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Revista Computación y Sistemas; Vol. 1 No. 3
publisher.none.fl_str_mv Revista Computación y Sistemas; Vol. 1 No. 3
dc.source.none.fl_str_mv reponame:Repositorio Digital del IPN
instname:Instituto Politécnico Nacional
instacron:IPN
instname_str Instituto Politécnico Nacional
instacron_str IPN
institution IPN
reponame_str Repositorio Digital del IPN
collection Repositorio Digital del IPN
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1858176747423399936
score 15,811543

Similares en LA Referencia