Follow
Hubert Ramsauer
Hubert Ramsauer
Research Assistant at Institute for Machine Learning, Johannes Kepler University Linz
Verified email at ml.jku.at - Homepage
Title
Cited by
Cited by
Year
Gans trained by a two time-scale update rule converge to a local nash equilibrium
M Heusel, H Ramsauer, T Unterthiner, B Nessler, S Hochreiter
Advances in neural information processing systems 30, 2017
80162017
Hopfield networks is all you need
H Ramsauer, B Schäfl, J Lehner, P Seidl, M Widrich, T Adler, L Gruber, ...
arXiv preprint arXiv:2008.02217, 2020
2372020
Coulomb gans: Provably optimal nash equilibria via potential fields
T Unterthiner, B Nessler, C Seward, G Klambauer, M Heusel, ...
arXiv preprint arXiv:1708.08819, 2017
782017
Modern hopfield networks and attention for immune repertoire classification
M Widrich, B Schäfl, M Pavlović, H Ramsauer, L Gruber, M Holzleitner, ...
Advances in Neural Information Processing Systems 33, 18832-18845, 2020
682020
Gans trained by a two time-scale update rule converge to a local nash equilibrium. arXiv 2017
M Heusel, H Ramsauer, T Unterthiner, B Nessler, S Hochreiter
arXiv preprint arXiv:1706.08500, 0
47
Cloob: Modern hopfield networks with infoloob outperform clip
A Fürst, E Rumetshofer, J Lehner, VT Tran, F Tang, H Ramsauer, D Kreil, ...
Advances in neural information processing systems 35, 20450-20468, 2022
362022
omas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium
M Heusel, H Ramsauer
Advances in Neural Information Processing Systems, 6626-6637, 0
5
A GAN based solver of black-box inverse problems
M Gillhofer, H Ramsauer, J Brandstetter, B Schäfl, S Hochreiter
NeurIPS 2019 Workshop on Solving Inverse Problems with Deep Networks, 2019
22019
About gradient based importance weighting in feed-forward artificial neural networks/submitted by Hubert Ramsauer
H Ramsauer
Universität Linz, 2017
2017
The system can't perform the operation now. Try again later.
Articles 1–9