From 32eed15e918d70aa5a6c2df2f9cb0e8bc00f8a3a Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Wed, 2 Oct 2019 16:06:48 +0200 Subject: [PATCH] Changed to active voice Signed-off-by: Jim Martens --- body.tex | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/body.tex b/body.tex index 7fc5026..a478086 100644 --- a/body.tex +++ b/body.tex @@ -456,8 +456,8 @@ Liu et al.~\cite{Liu2016}. \section{Bayesian SSD for Model Uncertainty} -Networks trained with dropout are a general approximate Bayesian model~\cite{Gal2017}. As such, they can be used for everything a true -Bayesian model could be used for. This idea is applied to \gls{SSD} by Miller et al.: two dropout layers are added to \gls{vanilla} \gls{SSD}, after the layers fc6 and fc7 respectively (see figure \ref{fig:bayesian-ssd}). +Networks trained with dropout are a general approximate Bayesian model~\cite{Gal2017} and can be used for everything a true +Bayesian model could be used for. Miller et al. apply this idea to \gls{SSD}: two dropout layers are added to \gls{vanilla} \gls{SSD}, after the layers fc6 and fc7 respectively (see figure \ref{fig:bayesian-ssd}). \begin{figure} \centering