• Deep Learning for Transfer Learning and Time-Series Analysis

    School of Computing, University of Kent since 03/2016

    I am currently on a research visit in the labs of Caroline Li and Prof. Yi-Ke Guo and work on unsupervised learning methods for analysis of time-series data such as EEG.Implementation of our approaches is realized in TensorFlow and TensorLayer.

  • Deep Learning for Medical Computer Vision

    Institute of Imaging and Computer Vision, Aachen since 05/2016

    Within the ILUMINATE project, I am working on deep learning algorithms for semi-supervised dense classification of histopathological images used in cancer research. Apart from deployment of networks in our software system, I worked on a novel approaches to apply deep learning in contexts with little available labeled training data. Used software packages are mainly Theano and TensorFlow.

  • Teaching Assistant Positions

    RWTH Aachen University 09/2014 - 06/2015

    Winter Term 2014: Mathematical Methods in Electrical Engineering, Prof. Merhof, Institute of Imaging and Computer Vision, Aachen, Summer Term 2015: Fundamentals of Electrical Engineering II, Prof. DeDoncker, ISEA, Aachen

  • Computer Vision for Robotics, Software Intern

    Institute for Real-Time Learning Systems, University Siegen Summer 2013

    Development of a software system for automated calibration of 3D camera systems as a preparation for sensor fusion algorithms, using C++, the Point Cloud Library and ROS.


  • Student Engineer, Perception and Sensor Group

    TUfast e. V. Driverless Racing Team 2016 - present

    At TUfast, we are developing an autonomous version of a Formula Student Racecar to participate in the Formula Student Driverless competition in Hockenheim. I work in the Sensors and Perception group on deep learning approaches for processing of sensor inputs.

  • Student Engineer, Control Systems

    Formula Student Team RWTH Aachen e. V. 2014 - 2016

    I worked on the hardware and software design of data acquisition devices and the battery management system in the Formula Student racecars eace04 and eace05.

  • Founder and Project Manager

    IT4Kids, Enactus Aachen e. V. since 2013

    To provide children in primary school with courses in computer science, I founded IT4Kids in 2013 and build up the student initiative that is still active in Aachen as of now. With our classes, we have reached hundreds of pupils. The project was awarded the 3rd place at the Enactus National Competition 2015 and a winning project in the Google Impact Challenge (awarded 10.000 €). We also started the development of a flexible programming environment for pupils, combining advantages of Scratch and Python.

Publications and Talks

Das TUfast Driverless Team entwickelt seit letztem Jahr an einem vollautomatischen Fahrzeug, das im August in einem internationalen Wettbewerb am Hockenheimring teilnehmen wird. Im Rahmen dieses Vortrags werden wir Ihnen zunächst generelle Einblicke in die Entwicklung eines autonomen Formula Student Wagens geben und einen Überblick vermitteln, welche Komponenten auf dem Weg vom konventionellen Fahrzeug zum vollautomatischen Rennwagen nötig sind. Im zweiten Teil des Vortrags stellen wir das Sensorsystem des Wagens im Detail vor, verbunden mit einer Einführung in die Verwendung von Deep Learning Algorithmen für Bildsegmentierung zur Erkennung der befahrbaren Strecke in Echtzeit. Neben den am Ende angewandten Algorithmen selbst werden wir auch die in der Praxis relevanten Ansätze zur Akquise von annotierten Daten durch den Einsatz von klassischer Bildverarbeitung und Weakly-Supervised Learning vorstellen.

Um nicht nur die Hyperlinkstruktur des Webs zur Suche nach Informationen zu verwenden, werden bei Google fortgeschrittene Methoden zur semantischen Analyse von Webseiten verwendet. Da es nicht sicher bekannt ist, welche Methoden am Ende in welche Ausführung zum Einsatz kommen, soll dieser Vortrag als generelle Einführung in das Verarbeiten und Suchen nach Informationen in Texten in Form einer Einführung in Natural Language Processing, Latenter Semantischer Analyse und neuen Fortschritten auf dem Bereich des Machine Learning geben. In der wirklichen Pipeline von Google werden viele dieser Methoden in weiterentwickelten Formen zum Einsatz kommen. Als wichtigste Modelle, um Wörter, Dokumente und Suchanfragen in einen latenten Vektorraum zu projizieren, in dem semantische und syntaktische Zusammenhänge möglichst akkurat durch lineare Operationen wiedergegeben werden können, wird das word2vec und GloVe Modell theoretisch und anhand praktischer Beispiele eingeführt. Ein Ausblick zur Verwendung von Deep Learning Modellen für End-to- End Learning von Dokumentenembeddings und dem Semantischen Hashing schließt den Vortrag ab.

Compressed sensing has proven to be an important technique in signal acquisition, especially in contexts in which sensor quality or the maximum possible duration of the measurement is limited. In this report, deep learning techniques are used to improve compressive sensing in the context of image acquisition. In a previous approach, stacked denoising autoencoders capable of reconstructing images considerably faster than conventional iterative methods were deployed. Apart from reviewing this approach, a possible extension using convolutional autoencoders inspired by the popular VGGnet architecture is discussed. Instead of learning models from scratch, a simple yet effective way for adapting available filters used in ImageNet classification is presented. By reformulation of the autoencoder structure in terms of a fully convolutional network, the previous approach can be adapted to arbritrarly large images for efficient learning of the measurement matrix and sparsity basis. Suggestions on the real implementation of such as system conclude the report.

In this thesis, various methods for the design of deep architectures for tissue classification are presented. By using transfer learning and unsupervised feature learning, it is shown that powerful state of the art models with millions of parameters can be finetuned to outperform previous approaches despite the lack of sufficient labeled training examples. Several models such as the 16-layer VGGnet, the GoogLeNet model with some exten- sion, convolutional restrict boltzman machines and convolutional denoising autoencoders were trained on the ILUMINATE-9 dataset. Along with evidence provided on how the training policy for the networks should be designed, a whole model zoo, trained on the ILUMINATE-9 dataset, is provided along with this thesis.


TUFast Driverless nb017

Development of a fully autonomous racecar for the FSG Driverless competition in Hockenheim.


M.Sc. Neuroengineering Student Blog with latest information about our study program and events.

Ecurie Aix eace04/05

Contributions include the design of electric control units


ILUMINATE develops a novel platform for integrated analysis of in-vivo models for preclinical evaluation of new compounds in oncology, including innovative therapeutic approaches in oncoimmunology.


IT4Kids provides computer science classes to elementary school pupils - Providing software, teaching materials and easy communication between schools and teaching students