Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation
Viktor Bengs - NeurIPS 2022
The UAI reading group is a great opportunity for researchers and students who are eager to learn and present recent works about uncertainty estimation in AI.
How to attend UAI reading group?
- Time: we meet on Mondays between 5:30pm and 6:30pm. You ca find the exact schedule below.
- Location: we meet on-line via this zoom room.
- Youtube channel: we publish the recordings of talks on the UAI Youtube channel. Feel free to check it out!
How to present at UAI reading group?
- Contact details: send an email to jpostels@ethz.ch and bcharpentier@tum.de.
- Presentation format: 30-60min with interactive questions.
-
-
Deep Ensembles Work, But Are They Necessary?
E. Kelly Buchanan - NeurIPS 2022
-
Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction
Masha Itkina - CoRL 2022
-
Uncertainty-Aware Reinforcement Learning for Risk-Sensitive Player Evaluation in Sports Game
Yudong Luo - NeurIPS 2022
-
Masksembles for Uncertainty Estimation
Nikita Durasov - CVPR 2021
-
NOMU - Neural Optimization-based Model Uncertainty
Jakob Heiss - ICML 2022
-
An Impartial Take to the CNN vs Transformer Robustness Contest
Francesco Pinto - ECCV 2022