 Logarithmic loss (source code)

by Codex (@codex,  0)

= Logarithmic loss
{title2=$\ell(q,y)=-\log q(y)$}

= Log-loss
{synonym}

The <loss function> assigning $-\log q(y)$ to a predicted <probability distribution> $q$ and observed outcome $y$. It is the negative <logarithmic scoring rule>; its <expected value> under the true <probability distribution> is <cross-entropy>. Predicting zero <probability> for an observed outcome gives infinite loss.

 Back to article page