User profiles for Hubert Ramsauer
Hubert RamsauerResearch Assistant at Institute for Machine Learning, Johannes Kepler University Linz Verified email at ml.jku.at Cited by 12344 |
Gans trained by a two time-scale update rule converge to a local nash equilibrium
Generative Adversarial Networks (GANs) excel at creating realistic images with complex
models for which maximum likelihood is infeasible. However, the convergence of GAN training …
models for which maximum likelihood is infeasible. However, the convergence of GAN training …
Hopfield networks is all you need
We introduce a modern Hopfield network with continuous states and a corresponding
update rule. The new Hopfield network can store exponentially (with the dimension of the …
update rule. The new Hopfield network can store exponentially (with the dimension of the …
Cloob: Modern hopfield networks with infoloob outperform clip
CLIP yielded impressive results on zero-shot transfer learning tasks and is considered as a
foundation model like BERT or GPT3. CLIP vision models that have a rich representation are …
foundation model like BERT or GPT3. CLIP vision models that have a rich representation are …
Modern hopfield networks and attention for immune repertoire classification
A central mechanism in machine learning is to identify, store, and recognize patterns. How
to learn, access, and retrieve such patterns is crucial in Hopfield networks and the more …
to learn, access, and retrieve such patterns is crucial in Hopfield networks and the more …
Coulomb GANs: Provably optimal Nash equilibria via potential fields
Generative adversarial networks (GANs) evolved into one of the most successful unsupervised
techniques for generating realistic images. Even though it has recently been shown that …
techniques for generating realistic images. Even though it has recently been shown that …
A GAN based solver of black-box inverse problems
We propose a GAN based approach to solve inverse problems which have non-differential
or non-continuous forward relations. In the standard sense, an inverse problem is interpreted …
or non-continuous forward relations. In the standard sense, an inverse problem is interpreted …
Why current rain denoising models fail on CycleGAN created rain images in autonomous driving
M Kranl, H Ramsauer, B Knapp - arXiv preprint arXiv:2305.12983, 2023 - arxiv.org
One of the main tasks of an autonomous agent in a vehicle is to correctly perceive its
environment. Much of the data that needs to be processed is collected by optical sensors such as …
environment. Much of the data that needs to be processed is collected by optical sensors such as …
Estimation of factor models with incomplete data and their applications
FH Ramsauer - 2017 - mediatum.ub.tum.de
This dissertation estimates factor models with incomplete data. In this context, hidden factors
map serial and cross-sectional correlations of financial and macroeconomic data. The …
map serial and cross-sectional correlations of financial and macroeconomic data. The …
About gradient based importance weighting in feed-forward artificial neural networks/submitted by Hubert Ramsauer
H Ramsauer - 2017 - epub.jku.at
Training artificial neural networks is hard. To achieve high predictive capabilities on previously
unseen data, artificial neural networks need a big amount of samples to train on. And it …
unseen data, artificial neural networks need a big amount of samples to train on. And it …
[CITATION][C] International Conference on Learning Representations
H Ramsauer, B Schäfl, J Lehner, P Seidl, M Widrich… - 2021 - ICRL