cross-entropy
A generalization of Log Loss to multi-class classification problems.
Plain English Explanation
A generalization of Log Loss to multi-class classification problems. Cross-entropy quantifies the difference between two probability distributions. See also perplexity.
How is it used?
Practitioners refer to cross-entropy when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.