1 code implementation • 30 Aug 2024 • Daniel Haider, Felix Perfler, Vincent Lostanlen, Martin Ehler, Peter Balazs
Convolutional layers with 1-D filters are often used as frontend to encode audio signals.
1 code implementation • 22 Jun 2024 • Daniel Haider, Martin Ehler, Peter Balazs
Injectivity is the defining property of a mapping that ensures no information is lost and any input can be perfectly reconstructed from its output.
1 code implementation • 11 Sep 2023 • Daniel Haider, Vincent Lostanlen, Martin Ehler, Peter Balazs
Numerical simulations align with our theory and suggest that the condition number of a convolutional layer follows a logarithmic scaling law between the number and length of the filters, which is reminiscent of discrete wavelet bases.
2 code implementations • 25 Jul 2023 • Vincent Lostanlen, Daniel Haider, Han Han, Mathieu Lagrange, Peter Balazs, Martin Ehler
Waveform-based deep learning faces a dilemma between nonparametric and parametric approaches.
1 code implementation • 18 Jul 2023 • Daniel Haider, Martin Ehler, Peter Balazs
The paper uses a frame-theoretic setting to study the injectivity of a ReLU-layer on the closed ball of $\mathbb{R}^n$ and its non-negative part.
1 code implementation • 7 Nov 2022 • Anna Breger, Clemens Karner, Martin Ehler
The code is made available on GitHub and straightforward to use.
no code implementations • 13 Sep 2021 • Anna Breger, Felix Goldbach, Bianca S. Gerendas, Ursula Schmidt-Erfurth, Martin Ehler
The results underline the visual evaluation.
no code implementations • 2 Aug 2019 • José Ignacio Orlando, Anna Breger, Hrvoje Bogunović, Sophie Riedl, Bianca S. Gerendas, Martin Ehler, Ursula Schmidt-Erfurth
Supervised deep learning models trained with standard loss functions are usually able to characterize only the most common disease appeareance from a training set, resulting in suboptimal performance and poor generalization when dealing with unseen lesions.
1 code implementation • 22 Jan 2019 • Anna Breger, Jose Ignacio Orlando, Pavol Harar, Monika Dörfler, Sophie Klimscha, Christoph Grechenig, Bianca S. Gerendas, Ursula Schmidt-Erfurth, Martin Ehler
In two supervised learning problems, clinical image segmentation and music information classification, the application of our proposed augmented target loss functions increase the accuracy.
no code implementations • 17 Feb 2014 • Franz J. Király, Martin Ehler
We study phase retrieval from magnitude measurements of an unknown signal as an algebraic estimation problem.