EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning models and the limits of explainable artificial intelligence

Jens Christian Bjerring, Jakob Mainz, Lauritz Munch

Asian Journal of Philosophy · 30.01.2025 · 4 (1)

DOI: 10.1007/s44204-024-00238-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Asian Journal of Philosophy, online erschienen am 30.01.2025. Verfasst von Jens Christian Bjerring und 2 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Carlsbergfondet, Aarhus Universitet.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

It has often been argued that we face a trade-off between accuracy and opacity in deep learning models. The idea is that we can only harness the accuracy of deep learning models by simultaneously accepting that the grounds for the models’ decision-making are epistemically opaque to us. In this paper, we ask the following question: what are the prospects of making deep learning models transparent without compromising on their accuracy? We argue that the answer to this question depends on which kind of opacity we have in mind. If we focus on the standard notion of opacity, which tracks the internal complexities of deep learning models, we argue that existing explainable AI (XAI) techniques show us that the prospects look relatively good. But, as it has recently been argued in the literature, there is another notion of opacity that concerns factors external to the model. We argue that there are at least two types of external opacity—link opacity and structure opacity—and that existing XAI techniques can to some extent help us reduce the former but not the latter.

Förderung

  • Carlsbergfondet
  • Aarhus Universitet

Zitieren

APA

Bjerring, J. C., Mainz, J., & Munch, L. (2025). Deep learning models and the limits of explainable artificial intelligence. Asian Journal of Philosophy, 4(1). https://doi.org/10.1007/s44204-024-00238-8

Vancouver

Bjerring JC, Mainz J, Munch L. Deep learning models and the limits of explainable artificial intelligence. Asian Journal of Philosophy. 2025;4(1). doi:10.1007/s44204-024-00238-8

BibTeX
@article{Bjerring2025,
  author = {Bjerring, Jens Christian and Mainz, Jakob and Munch, Lauritz},
  title = {Deep learning models and the limits of explainable artificial intelligence},
  journal = {Asian Journal of Philosophy},
  year = {2025},
  volume = {4},
  number = {1},
  doi = {10.1007/s44204-024-00238-8}
}
Kostenlos starten →