diff --git a/book/prob.tex b/book/prob.tex
index 13186ed..a3129ae 100644
--- a/book/prob.tex
+++ b/book/prob.tex
@@ -459,7 +459,7 @@ \section{Generative Stories}
 make things interesting, consider a multiclass classification problem,
 with continuous features modeled by independent Gaussians.  Since the
 label can take values $1 \dots K$, you can use a discrete
-distribution (die roll) to model it (as opposed to the Bernoilli
+distribution (die roll) to model it (as opposed to the Bernoulli
 distribution from before):
 %
 \begin{enumerate}