2martens
/
masterthesis-latex
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fixed capitalisation after colons 

Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens 2019-09-24 15:40:35 +02:00
parent cb92f63775
commit bec9a6e82c
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
body.tex
View File

@ -44,7 +44,7 @@ class of any given input. In this thesis, I will work with both.
\begin{figure} \begin{figure}
\centering \centering
\includegraphics[scale=1.0]{open-set} \includegraphics[scale=1.0]{open-set}
\caption{Open set problem: The test set contains classes that \caption{Open set problem: the test set contains classes that
were not present during training time. were not present during training time.
Icons in this image have been taken from the COCO data set Icons in this image have been taken from the COCO data set
website (\url{https://cocodataset.org/\#explore}) and were website (\url{https://cocodataset.org/\#explore}) and were
@ -103,7 +103,7 @@ representation of the input and has to find a decompression
that reconstructs the input as accurate as possible. During that reconstructs the input as accurate as possible. During
training these auto-encoders learn to reproduce a certain group training these auto-encoders learn to reproduce a certain group
of object classes. The actual novelty detection takes place of object classes. The actual novelty detection takes place
during testing: Given an image, and the output and loss of the during testing: given an image, and the output and loss of the
auto-encoder, a novelty score is calculated. For some novelty auto-encoder, a novelty score is calculated. For some novelty
detection approaches the reconstruction loss is exactly the novelty detection approaches the reconstruction loss is exactly the novelty
score, others consider more factors. A low novelty score, others consider more factors. A low novelty
@ -259,7 +259,7 @@ can be gained with a technique named Monte Carlo Batch Normalisation (MCBN).
Consequently, this technique can be applied to any network that utilises Consequently, this technique can be applied to any network that utilises
standard batch normalisation. standard batch normalisation.
Li et al.~\cite{Li2019} investigated the problem of poor performance Li et al.~\cite{Li2019} investigated the problem of poor performance
when combining dropout and batch normalisation: Dropout shifts the variance when combining dropout and batch normalisation: dropout shifts the variance
of a neural unit when switching from train to test, batch normalisation of a neural unit when switching from train to test, batch normalisation
does not change the variance. This inconsistency leads to a variance shift which does not change the variance. This inconsistency leads to a variance shift which
can have a larger or smaller impact based on the network used. can have a larger or smaller impact based on the network used.