Beta. Content is under active construction and has not been peer-reviewed. Report errors on
GitHub
.
Disclaimer
Theorem
Path
Curriculum
Paths
Demos
Diagnostic
Search
Quiz Hub
/
Softmax and Numerical Stability
Softmax and Numerical Stability
1 questions
Difficulty 3-3
View topic
Foundation
0 / 1
1 foundation
Adapts to your performance
1 / 1
foundation (3/10)
conceptual
What does the softmax function do when applied to a vector of real-valued scores (logits)?
Hide and think first
A.
It applies a hard winner-take-all operation, setting the largest score to 1 and all others to 0
B.
It centers the logits by subtracting the mean score from each element of the vector
C.
It clips all scores to lie within the range [0, 1] by clamping values at the boundaries
D.
It exponentiates each score and normalizes by the sum, producing a probability distribution over classes
Submit Answer