Constructing explainable classifiers from the start: enabling human-in-the loop machine learning

Interactive machine learning (IML) enables the incorporation of human expertise because the human participates in the construction of the learned model. Moreover, with human-in-the-loop machine learning (HITL-ML), the human experts drive the learning, and they can steer the learning objective not on...

Descripción completa

Detalles Bibliográficos
Autores: Estivill-Castro, V. (Vladimir), Gilmore, Eugene, Hexel, René
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/55636
Acceso en línea:http://hdl.handle.net/10230/55636
http://dx.doi.org/10.3390/info13100464
Access Level:acceso abierto
Palabra clave:Interactive machine learning
Decision tree classifiers
Transparent-by-design
Parallel coordinates
id ES_d7a63945f611fbdfdfffe623206787c8
oai_identifier_str oai:recercat.cat:10230/55636
network_acronym_str ES
network_name_str España
repository_id_str
spelling Constructing explainable classifiers from the start: enabling human-in-the loop machine learningEstivill-Castro, V. (Vladimir)Gilmore, EugeneHexel, RenéInteractive machine learningDecision tree classifiersTransparent-by-designParallel coordinatesInteractive machine learning (IML) enables the incorporation of human expertise because the human participates in the construction of the learned model. Moreover, with human-in-the-loop machine learning (HITL-ML), the human experts drive the learning, and they can steer the learning objective not only for accuracy but perhaps for characterisation and discrimination rules, where separating one class from others is the primary objective. Moreover, this interaction enables humans to explore and gain insights into the dataset as well as validate the learned models. Validation requires transparency and interpretable classifiers. The huge relevance of understandable classification has been recently emphasised for many applications under the banner of explainable artificial intelligence (XAI). We use parallel coordinates to deploy an IML system that enables the visualisation of decision tree classifiers but also the generation of interpretable splits beyond parallel axis splits. Moreover, we show that characterisation and discrimination rules are also well communicated using parallel coordinates. In particular, we report results from the largest usability study of a IML system, confirming the merits of our approach.MDPI202320232022info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/55636http://dx.doi.org/10.3390/info13100464reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésInformation. 2022;13(10):464.https://github.com/eugene-gilmore/dtc-survey-results© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:10230/556362026-05-29T05:05:01Z
dc.title.none.fl_str_mv Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
title Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
spellingShingle Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
Estivill-Castro, V. (Vladimir)
Interactive machine learning
Decision tree classifiers
Transparent-by-design
Parallel coordinates
title_short Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
title_full Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
title_fullStr Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
title_full_unstemmed Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
title_sort Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
dc.creator.none.fl_str_mv Estivill-Castro, V. (Vladimir)
Gilmore, Eugene
Hexel, René
author Estivill-Castro, V. (Vladimir)
author_facet Estivill-Castro, V. (Vladimir)
Gilmore, Eugene
Hexel, René
author_role author
author2 Gilmore, Eugene
Hexel, René
author2_role author
author
dc.subject.none.fl_str_mv Interactive machine learning
Decision tree classifiers
Transparent-by-design
Parallel coordinates
topic Interactive machine learning
Decision tree classifiers
Transparent-by-design
Parallel coordinates
description Interactive machine learning (IML) enables the incorporation of human expertise because the human participates in the construction of the learned model. Moreover, with human-in-the-loop machine learning (HITL-ML), the human experts drive the learning, and they can steer the learning objective not only for accuracy but perhaps for characterisation and discrimination rules, where separating one class from others is the primary objective. Moreover, this interaction enables humans to explore and gain insights into the dataset as well as validate the learned models. Validation requires transparency and interpretable classifiers. The huge relevance of understandable classification has been recently emphasised for many applications under the banner of explainable artificial intelligence (XAI). We use parallel coordinates to deploy an IML system that enables the visualisation of decision tree classifiers but also the generation of interpretable splits beyond parallel axis splits. Moreover, we show that characterisation and discrimination rules are also well communicated using parallel coordinates. In particular, we report results from the largest usability study of a IML system, confirming the merits of our approach.
publishDate 2022
dc.date.none.fl_str_mv 2022
2023
2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/55636
http://dx.doi.org/10.3390/info13100464
url http://hdl.handle.net/10230/55636
http://dx.doi.org/10.3390/info13100464
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Information. 2022;13(10):464.
https://github.com/eugene-gilmore/dtc-survey-results
dc.rights.none.fl_str_mv https://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869421024859127808
score 15,811543

Similares en LA Referencia