Zur JKU Startseite
Institut für Machine Learning
Was ist das?

Institute, Schools und andere Einrichtungen oder Angebote haben einen Webauftritt mit eigenen Inhalten und Menüs.

Um die Navigation zu erleichtern, ist hier erkennbar, wo man sich gerade befindet.

Hubert Ramsauer, MSc

Forschungsthemen

  • Deep Learning and Neural Networks
  • Few-Shot Learning
  • Domain Adaptation 
  • Hopfield Networks
  • Attention Mechanisms
  • Transformers
  • Generative Models

Ausgewählte Publikationen

  • Hubert Ramsauer, Bernhard Schäfl, Johannes Lehner, Philipp Seidl, Michael Widrich, Lukas Gruber, Markus Holzleitner, Milena Pavlović, Geir Kjetil Sandve, Victor Greiff, David Kreil, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter (2020). Hopfield Networks is All You Need. arXiv preprint arXiv:2008.02217 [PDF, öffnet eine externe URL in einem neuen Fenster]
  • Michael Widrich, Bernhard Schäfl, Hubert Ramsauer, Milena Pavlović, Lukas Gruber, Markus Holzleitner, Johannes Brandstetter, Geir Kjetil Sandve, Victor Greiff, Sepp Hochreiter, Günter Klambauer (2020). Modern Hopfield Networks and Attention for Immune Repertoire Classification. Accepted at 2020 on Conference on Advances in Neural Information Processing Systems. [PDF], öffnet eine externe URL in einem neuen Fenster
  • Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, Sepp Hochreiter (2017). GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. Accepted at 2017 on Conference on Advances in Neural Information Processing Systems. [PDF], öffnet eine externe URL in einem neuen Fenster
  • Thomas Unterthiner, Bernhard Nessler, Calvin Seward, Günter Klambauer, Martin Heusel, Hubert Ramsauer, Sepp Hochreiter (2018). Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields. Accepted at 2018 on International Conference of Learning Representations. [PDF], öffnet eine externe URL in einem neuen Fenster
  • Hubert Ramsauer, Johannes Brandstetter, Michael Gillhofer, Bernhard Schäfl, Sepp Hochreiter (2019). A GAN based solver idea for derivative-free optimization problems. NeurIPS 2019 Workshop: Science meets Engineering of Deep Learning
  • Michael Gillhofer, Hubert Ramsauer, Johannes Brandstetter, Bernhard Schäfl, Sepp Hochreiter (2019). A GAN based solver of black-box inverse problems. NeurIPS 2019 Workshop: Solving inverse problems with deep networks

Lehre

  • 2020: Lecture in LSTM and Recurrent Neural Nets, Co-Lecturer, JKU Linz
  • 2020: Exercises in LSTM and Recurrent Neural Nets, Co-Lecturer, JKU Linz
  • 2019: Lecture in LSTM and Recurrent Neural Nets, Co-Lecturer, JKU Linz
  • 2019: Exercises in LSTM and Recurrent Neural Nets, Co-Lecturer, JKU Linz
  • 2018: Exercises in Theoretical Concepts of Machine Learning, Co-Lecturer, JKU Linz
  • 2018: Exercises in Machine Learning: Unsupervised Techniques, Co-Lecturer, JKU Linz
  • 2017: Lecture in Theoretical Concepts of Machine Learning, Co-Lecturer, JKU Linz
  • 2017: Exercises in Theoretical Concepts of Machine Learning, Co-Lecturer, JKU Linz