From bfe85a9c4a6af90bd1283efe710fe86d6e0fd07a Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Tue, 24 Sep 2019 15:41:31 +0200 Subject: [PATCH] Improved understanding Signed-off-by: Jim Martens --- body.tex | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/body.tex b/body.tex index d326f1b..09c6cab 100644 --- a/body.tex +++ b/body.tex @@ -79,7 +79,7 @@ Technically there are two slightly different approaches that deal with this type of task: model uncertainty and novelty detection. Model uncertainty can be measured, for example, with dropout sampling. -Dropout is usually used only during training but +Dropout layers are usually used only during training but Miller et al.~\cite{Miller2018} use them also during testing to achieve different results for the same image making use of multiple forward passes. The output scores for the forward passes