StackedML
Practice
Labs
Questions
Models
Pricing
Sign in
Questions
/
Math Foundations
/
Calculus
/
Loss functions
← Previous
Next →
69.
Binary Cross-Entropy Loss
easy
Binary cross-entropy loss is defined as -[y·log(p) + (1-y)·log(1-p)]. What does it measure?
A
The KL divergence between the predicted distribution and the uniform distribution over two classes
B
The negative log-likelihood of the observed binary label under the predicted probability p
C
The absolute difference between the predicted probability and the true binary label
D
The squared difference between the predicted probability and the true binary label
Sign in to verify your answer
← Back to Questions