Login / Signup
On the Difficulty of Epistemic Uncertainty Quantification in Machine Learning: The Case of Direct Uncertainty Estimation through Loss Minimisation.
Viktor Bengs
Eyke Hüllermeier
Willem Waegeman
Published in:
CoRR (2022)
Keyphrases
</>
machine learning
inherent uncertainty
expected utility
pattern recognition
uncertain data
feature selection
decision theory
neural network
computer vision
reinforcement learning
parameter estimation
inductive learning
belief functions
robust optimization