Caesar AI Atlas

Cross-entropy

Also known as: Cross entropy

Caesar AI Atlas Definition

Cross-entropy is a loss function that measures the difference between a predicted probability distribution and a target distribution. It is widely used in classification and language modeling, including multi-class tasks.

Other Definitions

Cross-entropy Source

A generalization of Log Loss to multi-class classification problems. Cross-entropy quantifies the difference between two probability distributions. See also perplexity.

Related Terms