From dd654bb5b529a7141aad7f8647ae10fc4cd56085 Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Tue, 1 Oct 2019 13:28:12 +0200 Subject: [PATCH] Added info about source of inspiration for background section Signed-off-by: Jim Martens --- body.tex | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/body.tex b/body.tex index 0792818..53c11a7 100644 --- a/body.tex +++ b/body.tex @@ -335,7 +335,9 @@ procedure to select prior variances. \end{table} This section will use the \textbf{notation} defined in table -\ref{tab:notation} on page \pageref{tab:notation}. +\ref{tab:notation} on page \pageref{tab:notation}. The subsections +"Dropout Variational Inference" and "Dropout Sampling for Object Detection" +follow the theoretical explanation by Miller et al.~\cite{Miller2018}. To understand dropout sampling, it is necessary to explain the idea of Bayesian neural networks. They place a prior distribution over the network weights, for example a Gaussian prior distribution: