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

Removed wrong usage of effectively

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-10-04 13:47:34 +02:00
parent dc976932f8
commit 6b52dc8669
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
body.tex
View File

@ -16,7 +16,7 @@ algorithmic accountability~\cite{Diakopoulos2014}.
Supervised neural networks learn from input-output relations and
figure out by themselves what connections are necessary for that.
This feature is also their Achilles heel: it makes them effectively
This feature is also their Achilles heel: in effect, it makes them
black boxes and prevents any answers to questions of causality.
However, these questions of causality are of enormous consequence when
@ -54,8 +54,8 @@ class of any given input. In this thesis, I will work with both.
More specifically, I will look at object detection in the open set
conditions (see figure \ref{fig:open-set}).
In non-technical terms this effectively describes
the conditions \gls{CCTV} and robots outside of a laboratory operate in. In both cases images are recorded with cameras. In order to detect objects, a neural network has to analyse the images
In non-technical terms, this describes
the conditions \gls{CCTV}, and robots outside of a laboratory operate in. In both cases images are recorded with cameras. In order to detect objects, a neural network has to analyse the images
and return a list of detected and classified objects that it
finds in the images. The problem here is that networks can only
classify what they know. If presented with an object type that
@ -636,7 +636,7 @@ For this thesis, weights pre-trained on the sub data set trainval35k of the
COCO data set are used. These weights have been created with closed set
conditions in mind, therefore, they have been sub-sampled to create
an open set condition. To this end, the weights for the last
20 classes have been thrown away, making these classes effectively unknown.
20 classes have been thrown away, making these classes, in effect, unknown.
All images of the minival2014 data set are used but only ground truth
belonging to the first 60 classes is loaded. The remaining 20
@ -840,7 +840,7 @@ is lower but in an insignificant way. The rest of the performance metrics are
almost identical after rounding.
The results for Bayesian \gls{SSD} show a significant impact of \gls{NMS} or the lack thereof: maximum \(F_1\) score of 0.363 (with NMS) to 0.226
(without NMS). Dropout was disabled in both cases, making them effectively
(without NMS). Dropout was disabled in both cases, making them, in effect,
\gls{vanilla} \gls{SSD} with multiple forward passes.
With an open set error of 809, the Bayesian \gls{SSD} variant with disabled dropout and