Page Content
Bachelor Thesis: Henneberg, P. (2019). InfoGAN Disentanlement Framework
Title:
InfoGAN Disentanlement Framework
Description:
Image recognition and artificial image synthesis are a common field
of application where neural network architectures can be utilized to
solve the problem at hand. An aggravated extension
of image
synthesis deals with learning data representations in a way that the
features learned by the network represent human-interpretable
attributes of the data. This is called disentangled representation
learning and many different approaches have been pursued to solve
achieve that. This thesis provides the InfoGAN Disentanglement
Framework, an application encapsulating an InfoGAN architecture, which
is one of the aforementioned approaches. It utilizes concepts of
information theory to separate the desired features into a specified
code structure provided by the user of the framework. Furthermore, the
framework’s ability to find such disentangled representations is
demonstrated on different datasets of different size and complexity.
Lastly, a quantitative evaluation is performed, examining the effect
of parameter tuning on the quality of the disentanglement.
Supervisor: Boris Lorbeer [1], Tanja Hagemann [2]
Type: Bachelor Thesis
Duration: 4 months

Ernst-Reuter-Platz 7
10587 Berlin, Germany
Phone: +49 30 8353 58811
Fax: +49 30 8353 58409
e-mail query [4]
eer/parameter/en/font6/minhilfe/
mann/parameter/en/font6/minhilfe/
parameter/en/font6/minhilfe/id/207296/?no_cache=1&a
sk_mail=YrkKaQAI%2BOOcv84IfHEsMjQGCbLa83ey3fBpYslDi18%3
D&ask_name=TU%20Berlin%20-%20Service-centric%20Netw
orking%20-%20TEL%2019