M.Sc. Frederik Köhne

• project member (2021 – 2025)
• e-mail: Frederik.Koehne@uni-bayreuth.de

project: "Multilevel Architectures and Algorithms in Deep Learning"

• Artificial neural networks
• Optimization methods in machine learning

Publications

Preprints

Köhne, Frederik, Philipp, Friedrich M., Schaller, Manuel, Schiela, Anton and Worthmann, Karl: L∞-error bounds for approximations of the Koopman operator by kernel extended dynamic mode decomposition.. - Ilmenau ; Bayreuth, 2024-03-28. - 21 S.
doi:10.48550/arXiv.2403.18809

Köhne, Frederik, Kreis, Leonie, Schiela, Anton and Herzog, Roland: Adaptive Step Sizes for Preconditioned Stochastic Gradient Descent.. - Bayreuth ; Heidelberg, 2023-11. - 31 S.
doi:10.48550/arXiv.2311.16956

Herzog, Roland, Köhne, Frederik, Kreis, Leonie and Schiela, Anton: Frobenius-Type Norms and Inner Products of Matrices and Linear Maps with Applications to Neural Network Training.. - Bayreuth ; Heidelberg, 2023-11. - 14 S.
doi:10.48550/arXiv.2311.15419

Herberg, Evelyn, Herzog, Roland, Köhne, Frederik, Kreis, Leonie and Schiela, Anton: Sensitivity-Based Layer Insertion for Residual and Feedforward Neural Networks.. - Bayreuth ; Heidelberg, 2023-11. - 15 S.
doi:10.48550/arXiv.2311.15995

Herberg, Evelyn, Herzog, Roland and Köhne, Frederik: Time Regularization in Optimal Time Variable Learning.. - Heidelberg, 2023-06. - 9 S.
doi:10.48550/arXiv.2306.16111

Thesis    

Köhne, Frederik: Operatortheoretische Untersuchung kernbasierter Approximationsräume. - Bayreuth, 2022.
(Masterarbeit, 2022, Universität Bayreuth, Fakultät für Mathematik, Physik und Informatik)

M.Sc. Frederik Köhne
from 10/2021 until 09/2025: project member

Chair of Applied Mathematics
Department of Mathematics
University of Bayreuth
95440 Bayreuth, Germany

E-mail: Frederik.Koehne@uni-bayreuth.de