Skip to content

Glossary: Calculus for ML

Cross-entropy

Also written: log loss, cross entropy

A loss for yes-or-no predictions, -[y·log(p) + (1-y)·log(1-p)]. A confident wrong answer is punished heavily, and a confident right one costs almost nothing.

Where the book teaches it

Related terms

ProbabilitySigmoidLossMean squared error (MSE)