Fraunhofer Heinrich Hertz Institute 
   Dr. Nils Strodthoff
   Senior Research Scientist
Machine Learning Group
Department of Video Coding & Analytics
   Fraunhofer Institute for Telecommunications
Heinrich Hertz Institute HHI
Einsteinufer 37
10587 Berlin

Tel:  +49 30 31002-104
Fax: +49 30 31002-558

Google Scholar profile

Nils Strodthoff
   Short Bio 

Nils Strodthoff joined the Machine Learning Group at Fraunhofer Heinrich Hertz Institute as a research scientist in 2017. He studied physics at Georg-August-Universität Göttingen and Imperial College London (MSc 2009) from 2005 to 2009 and received the Dr. rer. nat. degree with distinction (summa cum laude) from Technische Universität Darmstadt in 2012. Focussing on non-perturbative quantum field theory, he held postdoctoral appointments at Ruprecht-Karls-Universität Heidelberg from 2012 to 2015 and Lawrence Berkeley National Laboratory, USA from 2016-2017 funded by a DFG research fellowship. He authored more than 25 peer-reviewed articles, presented at numerous international conferences, received scholarships from the Deutsche Studienstiftung and HGS-HIRe and was awarded the HGS-HIRe Excellence Award in 2011. He is a Machine Learning enthusiast and particularly interested in applications of Deep Learning in communications, biomedical signal processing and proteomics.


    Coverage of our article on detection of myocardial infarctions in ECG data:
technologyreviewAlgorithm matches human cardiologists in detecting heart attacks (02/07/2018)
heise Neuronales Netz erkennt Herzinfarkte so gut wie erfahrene Kardiologen (12/07/2018)
swr2 Künstliche Intelligenz erkennt Herzinfarkt so gut wie Facharzt (13/08/2018)

   Research Interests 
  • Machine Learning (ML), in particular Deep Learning
    from Computer Vision to Natural Language Processing (NLP)
  • Applications of ML in Communications
    for the physical layer: channel coding and feedback mechanisms
  • Applications of ML in Biomedical Data Analysis
    for ECG and other physiological data
  • Applications of ML in Proteomics
    in particular applications of self-supervised NLP-methods to sequence data
  • Applications of ML in Physics
    generative neural samplers for statistical physics and quantum field theory
  • Stabilized training of deep neural networks
    teacher-student setting, stability training,...
If you are interested in a MSc thesis in these areas, feel free to contact me.

  • Nils Strodthoff, Patrick Wagner, Markus Wenzel, and Wojciech Samek. Universal Deep Sequence Models for Protein Classification. bioRxiv preprint, 2019. URL bioRxiv.
  • Jan Laermann, Wojciech Samek, and Nils Strodthoff. Achieving Generalizable Robustness of Deep Neural Networks by Stability Training. arXiv preprint, 2019. URL arXiv.
  • Kim Nicoli, Pan Kessel, Nils Strodthoff, Wojciech Samek, Klaus-Robert Müller, and Shinichi Nakajima. Comment on "Solving Statistical Mechanics Using VANs": Introducing saVANt - VANs Enhanced by Importance and MCMC Sampling. arXiv Preprint, 2019. URL arXiv.

Journal publications:
  • Nils Strodthoff, Barış Göktepe, Thomas Schierl, Cornelius Hellge, and Wojciech Samek. Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G. CoRR, abs/1807.10495, 2018. URL arXiv, to appear in IEEE JSAC issue on Machine Learning in Wireless Communications.
  • Nils Strodthoff, and Claas Strodthoff. Detecting and interpreting myocardial infarction using fully convolutional neural networks. Physiological Measurement 40, no. 1, 015001, 2019. URL Publisher arXiv.

Conferences and workshops:
  • Nils Strodthoff, Barış Göktepe, Thomas Schierl, Cornelius Hellge, and Wojciech Samek. Machine Learning Techniques for Early HARQ Feedback Prediction in 5G. IEEE Global Communications Conference Workshops (GLOBECOM), 2018. URL Publisher.

  • Nils Strodthoff, Arun Shroff, and Wojciech Samek. Aspects of Evaluation Procedures for Machine Learning Algorithms. Input Document FGAI4H-D-039, 2019. URL FGAI4H-D-039.

For publications related to my work in high-energy physics/QCD see INSPIRE.
  Publishing Notes Data Protection Policy