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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/13/10/464 |
| _version_ | 1797472593784078336 |
|---|---|
| author | Vladimir Estivill-Castro Eugene Gilmore René Hexel |
| author_facet | Vladimir Estivill-Castro Eugene Gilmore René Hexel |
| author_sort | Vladimir Estivill-Castro |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-09T20:03:34Z |
| format | Article |
| id | doaj.art-21fe271b75c24550a55849cb5a54864d |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-09T20:03:34Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-21fe271b75c24550a55849cb5a54864d2023-11-24T00:35:59ZengMDPI AGInformation2078-24892022-09-01131046410.3390/info13100464Constructing Explainable Classifiers from the Start—Enabling Human-in-the Loop Machine LearningVladimir Estivill-Castro0Eugene Gilmore1René Hexel2Department of Information and Communications Technologies, Universitat Pompeu Fabra, 08018 Barcelona, SpainSchool of Information and Communication Technology, Griffith University, Brisbane 4111, AustraliaSchool of Information and Communication Technology, Griffith University, Brisbane 4111, AustraliaInteractive 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.https://www.mdpi.com/2078-2489/13/10/464interactive machine learningdecision tree classifierstransparent-by-designparallel coordinates |
| spellingShingle | Vladimir Estivill-Castro Eugene Gilmore René Hexel Constructing Explainable Classifiers from the Start—Enabling Human-in-the Loop Machine Learning Information interactive machine learning decision tree classifiers transparent-by-design parallel coordinates |
| title | 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_short | 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 |
| topic | interactive machine learning decision tree classifiers transparent-by-design parallel coordinates |
| url | https://www.mdpi.com/2078-2489/13/10/464 |
| work_keys_str_mv | AT vladimirestivillcastro constructingexplainableclassifiersfromthestartenablinghumanintheloopmachinelearning AT eugenegilmore constructingexplainableclassifiersfromthestartenablinghumanintheloopmachinelearning AT renehexel constructingexplainableclassifiersfromthestartenablinghumanintheloopmachinelearning |