Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty

By Jishnu Mukhoti, Andreas Kirsch, Joost R. van Amersfoort, Philip H. S. Torr, Yarin Gal. 2021

99 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Christian Henning
2. Benjamin Ehret
3. Gyuhak Kim
4. Maria R. Cervera
5. Johannes von Oswald
6. Francesco D'Angelo
7. Seijin Kobayashi
8. Benjamin F. Grewe

Citations in the corpus

• Posterior Meta-Replay for Continual Learning (2021, background): “This does not pose a problem in highly-curated ML datasets where samples with high aleatoric uncertainty are excluded [50], but drastically limits the applicability of entropy-based uncertainty estimation in more practical scenarios.”