no code implementations • 29 Apr 2024 • Pascal Fernsel, Željko Kereta, Alexander Denker
In this work, we show that score-based generative models (SGMs) can be used in a graduated optimisation framework to solve inverse problems.
no code implementations • 25 Apr 2021 • Pascal Fernsel
Classical approaches in cluster analysis are typically based on a feature space analysis.
no code implementations • ICLR 2019 • Jens Behrmann, Sören Dittmer, Pascal Fernsel, Peter Maass
We flip the usual approach to study invariance and robustness of neural networks by considering the non-uniqueness and instability of the inverse mapping.
no code implementations • 6 Aug 2018 • Pascal Fernsel, Peter Maass
Motivated by applications in hyperspectral imaging we investigate methods for approximating a high-dimensional non-negative matrix $\mathbf{\mathit{Y}}$ by a product of two lower-dimensional, non-negative matrices $\mathbf{\mathit{K}}$ and $\mathbf{\mathit{X}}.$ This so-called non-negative matrix factorization is based on defining suitable Tikhonov functionals, which combine a discrepancy measure for $\mathbf{\mathit{Y}}\approx\mathbf{\mathit{KX}}$ with penalty terms for enforcing additional properties of $\mathbf{\mathit{K}}$ and $\mathbf{\mathit{X}}$.
no code implementations • 25 Jun 2018 • Jens Behrmann, Sören Dittmer, Pascal Fernsel, Peter Maaß
Studying the invertibility of deep neural networks (DNNs) provides a principled approach to better understand the behavior of these powerful models.