Skip to main content
Theorem
Path
Curriculum
Paths
Labs
Diagnostic
Case Study
Blog
Search
Sign in
Quiz Hub
/
Calibration and Uncertainty Quantification
Calibration and Uncertainty Quantification
3 selected
Difficulty 3-7
3 unseen
View topic
Foundation
New
0 answered
1 foundation
1 intermediate
1 advanced
Adapts to your performance
Question 1 of 3
120s
foundation (3/10)
conceptual
What does calibration mean for predicted probabilities?
Hide and think first
A.
The classifier must have the highest possible accuracy.
B.
Among cases predicted near
0.7
, about
70%
should be positive.
C.
All probabilities must be either
0
or
1
.
D.
The model's logits must have mean zero.
Show Hint
Submit Answer
I don't know