The paper introduces n-MeRCI, a normalized metric that scores predictive uncertainty by its average rescaled width after calibrating to a target coverage rate.
The limitations of deep learning in adversarial settings,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
n-MeRCI: A new Metric to Evaluate the Correlation Between Predictive Uncertainty and True Error
The paper introduces n-MeRCI, a normalized metric that scores predictive uncertainty by its average rescaled width after calibrating to a target coverage rate.