EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Review of Uncertainty Representation and Quantification in Neural Networks

Kaizheng Wang, Fabio Cuzzolin, Keivan Shariatmadar, David Moens, Hans Hallez

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-03 · 48 (3) · 2476-2495

DOI: 10.1109/tpami.2025.3626645 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-03. Verfasst von Kaizheng Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 196 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Effectively estimating the uncertainty attached to neural network predictions thus becomes essential to improve robustness, reliability, and trustworthiness. This paper provides an overview of various methodologies for representing, quantifying, and distinguishing two major types of uncertainties (namely, 'aleatoric' and 'epistemic' uncertainty) in neural networks. The review covers classical probabilistic techniques such as Bayesian neural networks and deep ensembles, methods from generalized probability that leverage uncertainty representations such as Dirichlet distributions, belief functions, random sets, probability intervals, and credal sets, among others. Additionally, interval-based approaches employing interval models are also examined. We discuss the strengths and limitations of various methodologies and identify promising research directions for potential future exploration.

Zitieren

APA

Wang, K., Cuzzolin, F., Shariatmadar, K., Moens, D., & Hallez, H. (2026). A Review of Uncertainty Representation and Quantification in Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(3), 2476-2495. https://doi.org/10.1109/tpami.2025.3626645

Vancouver

Wang K, Cuzzolin F, Shariatmadar K, Moens D, Hallez H. A Review of Uncertainty Representation and Quantification in Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(3):2476-2495. doi:10.1109/tpami.2025.3626645

BibTeX
@article{Wang2026,
  author = {Wang, Kaizheng and Cuzzolin, Fabio and Shariatmadar, Keivan and Moens, David and Hallez, Hans},
  title = {A Review of Uncertainty Representation and Quantification in Neural Networks},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {3},
  pages = {2476--2495},
  doi = {10.1109/tpami.2025.3626645}
}
Kostenlos starten →