Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Estivill-Castro, V. (Vladimir)
- dc.contributor.author Gilmore, Eugene
- dc.contributor.author Hexel, René
- dc.date.accessioned 2023-02-07T07:07:41Z
- dc.date.available 2023-02-07T07:07:41Z
- dc.date.issued 2022
- dc.description.abstract 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.
- dc.format.mimetype application/pdf
- dc.identifier.citation Estivill-Castro V, Gilmore E, Hexel R. Constructing explainable classifiers from the start: enabling human-in-the loop machine learning. Information. 2022;13(10):464. DOI: 10.3390/info13100464
- dc.identifier.doi http://dx.doi.org/10.3390/info13100464
- dc.identifier.issn 2078-2489
- dc.identifier.uri http://hdl.handle.net/10230/55636
- dc.language.iso eng
- dc.publisher MDPI
- dc.relation.ispartof Information. 2022;13(10):464.
- dc.relation.isreferencedby https://github.com/eugene-gilmore/dtc-survey-results
- dc.rights © 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/).
- dc.rights.accessRights info:eu-repo/semantics/openAccess
- dc.rights.uri https://creativecommons.org/licenses/by/4.0/
- dc.subject.keyword Interactive machine learning
- dc.subject.keyword Decision tree classifiers
- dc.subject.keyword Transparent-by-design
- dc.subject.keyword Parallel coordinates
- dc.title Constructing explainable classifiers from the start: enabling human-in-the loop machine learning
- dc.type info:eu-repo/semantics/article
- dc.type.version info:eu-repo/semantics/publishedVersion