Karl Schrader
Position: Research Assistant
E-mail: schrader -at- mia.uni-saarland.de
(please replace anti-spam -at- by @)
Address: Mathematical Image Analysis Group
Faculty of Mathematics and Computer Science,
Saarland University
Campus E1.7
66041 Saarbrücken, Germany
Office: Room 4.04
Building E1.7, Saarbr├╝cken Campus
see also Contact
Research Area


Conference Papers

  1. T. Alt, P. Peter, J. Weickert, K. Schrader:
    Translating numerical concepts for PDEs into neural architectures.
    To appear in A. Elmoataz, J. Fadili, Y. Quéau, J. Rabin, L. Simon (Eds.): Scale Space and Variational Methods in Computer Vision. Lecture Notes in Computer Science, Springer, Cham, 2021.
    Also available as arXiv:2103.15419 [math.NA], March 2021.
  2. Technical Reports

  3. T. Alt, K. Schrader, M. Augustin, P. Peter, J. Weickert:
    Connections between Numerical Algorithms for PDEs and Neural Networks.
    arXiv:2107.14742 [math.NA], July 2021.
  4. T. Alt, K. Schrader, J. Weickert, P. Peter, M. Augustin:
    Designing Rotationally Invariant Neural Networks from PDEs and Variational Methods.
    arXiv:2108.13993 [cs.LG], August 2021.
  5. Theses

  6. K. Schrader:
    Translating Anisotropic Diffusion into Residual Networks.
    M.Sc. Thesis in Visual Computing,
    Saarland University, Saarbrücken, Germany, October 2020.

  7. Courses