Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 237.02 KB
Add to list
  1. Search results
  2. Explainable black box models

Explainable black box models

Wim De Mulder
(2023) INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1. In Lecture notes in networks and systems 542. p.573-587
Author
Organization
Abstract
The idea that black box models are unexplainable has been elevated to an axiom. In contrast to explainable models, where the involved parameters have a certain meaning that is understandable, black box models rely on principles that have no other function than to produce sophisticated mappings. The lack of explainability is sometimes compensated by applying a so-called post-hoc explainability method. Such a method is supposed to extract some meaning from the separately constructed black box model, but this technique is criticized for several reasons. In this paper we argue that there is an alternative to explainable models and to post-hoc explainability, by representing explanations as variables at either the input side or the output side of a black box model. This results in explainable black box models, where explanations are unrelated to the working principles, but they are still part of that same black box model.
Keywords
Black box models, Explainability, DECISIONS

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 237.02 KB

Citation

Please use this url to cite or link to this publication:

MLA
De Mulder, Wim. “Explainable Black Box Models.” INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1, edited by Kohei Arai, vol. 542, Springer, 2023, pp. 573–87, doi:10.1007/978-3-031-16072-1_42.
APA
De Mulder, W. (2023). Explainable black box models. In K. Arai (Ed.), INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1 (Vol. 542, pp. 573–587). https://doi.org/10.1007/978-3-031-16072-1_42
Chicago author-date
De Mulder, Wim. 2023. “Explainable Black Box Models.” In INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1, edited by Kohei Arai, 542:573–87. Springer. https://doi.org/10.1007/978-3-031-16072-1_42.
Chicago author-date (all authors)
De Mulder, Wim. 2023. “Explainable Black Box Models.” In INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1, ed by. Kohei Arai, 542:573–587. Springer. doi:10.1007/978-3-031-16072-1_42.
Vancouver
1.
De Mulder W. Explainable black box models. In: Arai K, editor. INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1. Springer; 2023. p. 573–87.
IEEE
[1]
W. De Mulder, “Explainable black box models,” in INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1, Amsterdam, the Netherlands, 2023, vol. 542, pp. 573–587.
@inproceedings{01GMGJCPKX0TK0FKGJ67FSB4Y6,
  abstract     = {{The idea that black box models are unexplainable has been elevated to an axiom. In contrast to explainable models, where the involved parameters have a certain meaning that is understandable, black box models rely on principles that have no other function than to produce sophisticated mappings. The lack of explainability is sometimes compensated by applying a so-called post-hoc explainability method. Such a method is supposed to extract some meaning from the separately constructed black box model, but this technique is criticized for several reasons. In this paper we argue that there is an alternative to explainable models and to post-hoc explainability, by representing explanations as variables at either the input side or the output side of a black box model. This results in explainable black box models, where explanations are unrelated to the working principles, but they are still part of that same black box model.}},
  author       = {{De Mulder, Wim}},
  booktitle    = {{INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1}},
  editor       = {{Arai, Kohei}},
  isbn         = {{9783031160714}},
  issn         = {{2367-3370}},
  keywords     = {{Black box models,Explainability,DECISIONS}},
  language     = {{eng}},
  location     = {{Amsterdam, the Netherlands}},
  pages        = {{573--587}},
  publisher    = {{Springer}},
  title        = {{Explainable black box models}},
  url          = {{http://doi.org/10.1007/978-3-031-16072-1_42}},
  volume       = {{542}},
  year         = {{2023}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: