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

Improved spelling and wording

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-09-24 15:19:54 +02:00
parent 4a608bcef6
commit 43820194c8
1 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
body.tex
View File

@ -19,7 +19,7 @@ figure out by themselves what connections are necessary for that.
This feature is also their Achilles heel: it makes them effectively
black boxes and prevents any answers to questions of causality.
However, these questions of causility are of enormous consequence when
However, these questions of causality are of enormous consequence when
results of neural networks are used to make life changing decisions:
Is a correlation enough to bring forth negative consequences
for a particular person? And if so, what is the possible defence
@ -32,7 +32,7 @@ Such an explanation must come from the network or an attached piece
of technology to allow adoption in mass. Obviously this setting
poses the question, how such an endeavour can be achieved.
For neural networks there are fundamentally two type of tasks:
For neural networks there are fundamentally two types of tasks:
regression and classification. Regression deals with any case
where the goal for the network is to come close to an ideal
function that connects all data points. Classification, however,
@ -72,7 +72,7 @@ that the network was never trained on a particular type of object.
Therefore, it would be impossible for them to identify the output
of the network as false positive.
This goes back to the need for automatic explanation. Such a system
This reaffirms the need for automatic explanation. Such a system
should by itself recognise that the given object is unknown and
hence mark any classification result of the network as meaningless.
Technically there are two slightly different approaches that deal
@ -114,9 +114,11 @@ novelty score.
Auto-encoders work well for data sets like MNIST~\cite{Deng2012}
but perform poorly on challenging real world data sets
like MS COCO~\cite{Lin2014}. Therefore, a comparison between
model uncertainty and novelty detection is considered out of
scope for this thesis.
like MS COCO~\cite{Lin2014}, complicating any potential comparison between
them and object detection networks like SSD.
Therefore, a comparison between model uncertainty with a network like
SSD and novelty detection with auto-encoders is considered out of scope
for this thesis.
Miller et al.~\cite{Miller2018} used an SSD pre-trained on COCO
without further fine-tuning on the SceneNet RGB-D data