Question 1

What is cross-entropy loss?

Accepted Answer

Cross-entropy loss measures the difference between predicted probability distribution and true labels. It is widely used in classification tasks.

Question 2

How is binary cross-entropy calculated?

Accepted Answer

Binary cross-entropy = -[ y_true * log(p) + (1 - y_true) * log(1 - p) ], where y_true is 0 or 1 and p is predicted probability.

Question 3

What is categorical cross-entropy?

Accepted Answer

Categorical cross-entropy = - sum( y_true_i * log(p_i) ) over all classes, where y_true is one-hot encoded and p_i are predicted probabilities.

⚡ Cross-Entropy Loss Calculator