schließen

Ass.-Prof. Dr. Johannes Brandstetter

{{ dict().Publications }}

{{ typ[0].TYP }}

{{ dict().Lectures }}

{{ typ[0].TYP }}

{{ dict().ResearchProjects }}

{{ typ[0].TYP }}

{{ dict().Scs }}

{{ typ[0].TYP }}

{{ dict().Innovations }}

{{ typ[0].TYP }}

Curriculum Vitae

Forschungsthemen

  • Deep Learning
  • Deep Reinforcement Learning
  • Generative Adversarial Networks
  • Physics-inspired and physics-informed machine learning
  • Long Short-Term Memory

Ausgewählte Publikationen

  • Jose Arjona-Medina, Michael Gillhofer, Michael Widrich, Thomas Unterthiner, Johannes Brandstetter, and Sepp Hochreiter (2019). RUDDER: Return Decomposition for Delayed Rewards. Accepted at 2019 Conference on Advances in Neural Information Processing Systems[PDF]

Betreute Masterarbeiten 

  •  Analysis of Integral Probability Metrics for Generative Adversarial Networks, Lukas Gruber, ongoing

Lehre

  • 2018: Exercises in Machine Learning: Supervised Techniques, Lecturer, JKU Linz
  • 2018: Lecture in Numerical and Symbolic Methods for Bioinformatics, Lecturer, JKU Linz
  • 2019: Exercises in Machine Learning: Unsupervised Techniques, Lecturer, JKU Linz
  • 2019: Exercises in Theoretical Concepts of Machine Learning, Lecturer, JKU Linz
  • 2019: Lecture in Machine Learning: Supervised Techniques, Lecturer, JKU Linz
  • 2019: Exercises in Machine Learning: Supervised Techniques, Lecturer, JKU Linz
  • 2019: Lecture in Hands-on AI I, Lecturer, JKU Linz
  • 2019: Lecture in Programming in Python I, Co-Lecturer, JKU Linz
  • 2019: Exercises in Deep Learning and Neural Nets I, Co-Lecturer, JKU Linz

Vorträge und Externe Lehre

  • ÖAW AI Summer School 2019, Deep Learning Lecture series. (Homepage)
  1. [Introduction to Data Science] Introduction to Data Science
  2. [Introduction to Machine Learning] Introduction to Supervised Machine Learning
  3. [Deep Learning I] Logistic Regression
  4. [Deep Learning II] Neural Networks
  5. [Deep Learning III] Convolutional Neural Networks
  6. [Deep Learning IV] (Variational) Autoencoders and Generative Adversarial Networks
  7. [Deep Learning V] Recurrent Neural Networks

Persönliche Daten/Ausbildung

  • Born September 25, 1989
  • BSc in Technical Physics (TU Wien), July 2012
  • MSc in Technical Physics (TU Wien), November 2014
  • PhD in High Energy Physics (Vienna Institute of High Energy Physics, TU Wien), May 2018
  • PhD Thesis