Foto von Daniel Auge

Daniel Auge, M.Sc.

Technische Universität München


Boltzmannstr. 3
85748 Garching b. München

Curriculum Vitae

  • (2018-now) Ph.D. candidate, Technical University of Munich
  • (2018) Software Developer, Ibeo Automotive Systems GmbH
  • (2015-2017) Master of Science in Electrical Engineering, Hamburg University of Technology
  • (2011-2015) Bachelor of Science in General Engineering Science, Hamburg University of Technology

Research Interests

Development of spiking neural networks for the monitoring of analog radar sensor front ends.

Thesis Supervision




  • Master thesis: Winner-take-all Circuits in Spiking Neural Networks for Object Tracking in Event-based Video Data
  • Master thesis: Development of a Network Architecture for Speech Recognition Using Spiking Networks
  • Master thesis: Embedded AI - Development of a Toolchain for the Adaption of Neural Networks to the Requirements of Embedded Systems
  • Bachelor thesis: Developing an Annotation Tool for Machine Learning
  • Bachelor thesis: Radar Gesture Recognition with Hierarchical Temporal Memory



  • Hille, Julian; Auge, Daniel; Grassmann, Cyprian; Knoll, Alois: FMCW radar2radar Interference Detection with a Recurrent Neural Network. 2022 IEEE Radar Conference (RadarConf22), IEEE, 2022 mehr… BibTeX Volltext ( DOI ) Volltext (mediaTUM)
  • Mueller, Etienne; Auge, Daniel; Klimaschka, Simon; Knoll, Alois: Neural Oscillations for Energy-Efficient Hardware Implementation of Sparsely Activated Deep Spiking Neural Networks. Association for the Advancement of Artificial Intelligence (AAAI), 2022Practical Deep Learning in the Wild mehr… BibTeX Volltext (mediaTUM)
  • Mueller, Etienne; Auge, Daniel; Knoll, Alois: Exploiting Inhomogeneities of Subthreshold Transistors as Populations of Spiking Neurons. International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), 2022 mehr… BibTeX


  • Auge, Daniel; Hille, Julian; Mueller, Etienne; Knoll, Alois: A Survey of Encoding Techniques for Signal Processing in Spiking Neural Networks. Neural Processing Letters, 2021 mehr… BibTeX Volltext ( DOI ) Volltext (mediaTUM)
  • Daniel Auge, Julian Hille, Etienne Mueller, Alois Knoll: Hand Gesture Recognition in Range-Doppler Images Using Binary Activated Spiking Neural Networks. IEEE International Conference on Automatic Face and Gesture Recognition 2021, 2021accepted mehr… BibTeX Volltext (mediaTUM)
  • Daniel Auge, Julian Hille, Felix Kreutz, Etienne Mueller, Alois Knoll: End-to-end Spiking Neural Network for Speech Recognition Using Resonating Input Neurons. 30th International Conference on Artificial Neural Networks (ICANN), 2021accepted mehr… BibTeX Volltext (mediaTUM)
  • Etienne Mueller, Daniel Auge, Alois Knoll: Normalization Hyperparameter Search for Converted Spiking Neural Networks. Bernstein Conference, 2021 mehr… BibTeX Volltext ( DOI ) Volltext (mediaTUM)
  • Etienne Mueller, Julius Hansjakob, Daniel Auge, Alois Knoll: Minimizing Inference Time: Optimization Methods for Converted Deep Spiking Neural Networks. International Joint Conference on Neural Networks (IJCNN), 2021accepted mehr… BibTeX Volltext (mediaTUM)
  • Mueller, Etienne; Studenyak, Viktor; Auge, Daniel; Knoll, Alois: Spiking Transformer Networks: A Rate Coded Approach for Processing Sequential Data. Internation Conference on Systems and Informatics (ICSAI), 2021accepted mehr… BibTeX Volltext (mediaTUM)
  • Nair, Saasha; Shafaei, Sina; Auge, Daniel; Knoll, Alois: An Evaluation of “Crash Prediction Networks” (CPN) for Autonomous Driving Scenarios in CARLA Simulator. SafeAI 2021 - The AAAI's Workshop on Artificial Intelligence Safety, 2021, mehr… BibTeX Volltext (mediaTUM)


  • Auge D, Wenner P, Mueller E: Hand Gesture Recognition using Hierarchical Temporal Memory on Radar Sequence Data. Bernstein Conference 2020, 2020 mehr… BibTeX Volltext ( DOI )
  • Daniel Auge, Etienne Mueller: Resonate-and-Fire Neurons as Frequency Selective Input Encoders for Spiking Neural Networks. 2020, mehr… BibTeX Volltext (mediaTUM)
  • Mueller E, Hansjakob J, Auge D: Faster Conversion of Analog to Spiking Neural Networks by Error Centering. Bernstein Conference 2020, 2020 mehr… BibTeX Volltext ( DOI )