Updated introduction and made it more concise
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
parent
4fbe894527
commit
8fa51535af
48
body.tex
48
body.tex
|
@ -8,34 +8,21 @@ Famous examples like the automatic soap dispenser which does not
|
|||
recognize the hand of a black person but dispenses soap when presented
|
||||
with a paper towel raise the question of bias in computer
|
||||
systems~\cite{Friedman1996}. Related to this ethical question regarding
|
||||
the design of so called algorithms, a term often used in public
|
||||
discourse for applied neural networks, is the question of
|
||||
the design of so called algorithms is the question of
|
||||
algorithmic accountability~\cite{Diakopoulos2014}.
|
||||
|
||||
The charm of supervised neural networks, that they can learn from
|
||||
input-output relations and figure out by themselves what connections
|
||||
are necessary for that, is also their Achilles heel. This feature
|
||||
makes them effectively black boxes. It is possible to question the
|
||||
training environment, like potential biases inside the data sets, or
|
||||
the engineers constructing the networks but it is not really possible
|
||||
to question the internal calculations made by a network. On the one
|
||||
hand, one might argue, it is only math and nothing magical that
|
||||
happens inside these networks. Clearly it is possible, albeit a chore,
|
||||
to manually follow the calculations of any given trained network.
|
||||
After all it is executed on a computer and at the lowest level only
|
||||
uses basic math that does not differ between humans and computers. On
|
||||
the other hand not everyone is capable of doing so and more
|
||||
importantly it does not reveal any answers to questions of causality.
|
||||
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
|
||||
black boxes and prevents any answers to questions of causality.
|
||||
|
||||
However, these questions of causility are of enormous consequence when
|
||||
neural networks are used, for example, in predictive policing. Is a
|
||||
correlation, a coincidence, enough to bring forth negative consequences
|
||||
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
|
||||
against math? Similar questions can be raised when looking at computer
|
||||
vision networks that might be used together with so called smart
|
||||
CCTV cameras, for example, like those tested at the train station
|
||||
Berlin Südkreuz. What if a network implies you committed suspicious
|
||||
behaviour?
|
||||
CCTV cameras to discover suspicious activity.
|
||||
|
||||
This leads to the need for neural networks to explain their results.
|
||||
Such an explanation must come from the network or an attached piece
|
||||
|
@ -103,17 +90,17 @@ representation of the input and has to find a decompression
|
|||
that reconstructs the input as accurate as possible. During
|
||||
training these auto-encoders learn to reproduce a certain group
|
||||
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. A low novelty
|
||||
score signals a known object. The opposite is true for a high
|
||||
novelty score.
|
||||
|
||||
\subsection*{Research Question}
|
||||
|
||||
Given these two approaches to solve the explanation task of above,
|
||||
it comes down to performance. At the end of the day the best
|
||||
theoretical idea does not help in solving the task if it cannot
|
||||
be implemented in a performant way. Miller et al. have shown
|
||||
Both presented approaches describe one way to solve the aforementioned
|
||||
problem of explanation. They can be differentiated by measuring
|
||||
their performance: the best theoretical idea is useless if it does
|
||||
not perform well. Miller et al. have shown
|
||||
some success in using dropout sampling. However, the many forward
|
||||
passes during testing for every image seem computationally expensive.
|
||||
In comparison a single run through a trained auto-encoder seems
|
||||
|
@ -124,11 +111,10 @@ use the work of Miller et al. as baseline to compare against.
|
|||
They use the SSD~\cite{Liu2016} network for object detection,
|
||||
modified by added dropout layers, and the SceneNet
|
||||
RGB-D~\cite{McCormac2017} data set using the MS COCO~\cite{Lin2014}
|
||||
classes. Instead of dropout sampling my approach will use
|
||||
an auto-encoder for novelty detection with all else, like
|
||||
using SSD for object detection and the SceneNet RGB-D data set,
|
||||
being equal. With respect to auto-encoders a recent implementation
|
||||
of an adversarial auto-encoder~\cite{Pidhorskyi2018} will be used.
|
||||
classes. I will use a simple implementation of an auto-encoder and
|
||||
novelty detection to compare with the work of Miller et al.
|
||||
SSD for the object detection and SceneNet RGB-D as the data
|
||||
set are used for both approaches.
|
||||
|
||||
\paragraph{Hypothesis} Novelty detection using auto-encoders
|
||||
delivers similar or better object detection performance under open set
|
||||
|
|
Loading…
Reference in New Issue