Frederik Schubert, M. Sc.
Frederik Schubert left the Institut für Informationsverarbeitung.
Publications and research activities from the time after the departure are not listed here.

 

Frederik Schubert studied computer engineering at Leibniz University in Hannover. He completed his master's degree in July 2019 with a thesis entitled "Multi-Task Learning by Neural Transfer Reinforcement Learning".

He has been working on his doctorate at TNT since September 2019. His research focuses on Reinforcement Learning and Procedural Content Generation, but he has also done work on object detection, small data classification and the analysis of hyperspectral images.

Other activities

Supervised Theses

  • Unsupervised Domain-Specific Pre-Training for Object Detection
  • Option Discovery in Hierarchical Reinforcement Learning
  • Defektprädiktion von Leiterplatten mit Verfahren der künstlichen Intelligenz
  • Wireframe Reconstruction from Single Images
  • Hyperbolic Embeddings in Distributional Reinforcement Learning
  • Implementation and Analysis of Sequential Model-Based Optimisation Methods for the Calibration of Numerical Groundwater Flow Models
  • Few-Shot Anomaly Detection Using Neural Cellular Automata
  • Feature-basierte Kombination von mehreren Bildern zur Klassifikation mit wenigen Trainingsbeispielen
  • Guided Diffusion Models with Few Training Examples
  • AlphaZero for Simultaneous Perfect-Information Games