Thomas Unterthiner
Thomas Unterthiner
Google Research (Brain Team)
Verified email at
Cited by
Cited by
Fast and accurate deep network learning by exponential linear units (ELUs)
DA Clevert, T Unterthiner, S Hochreiter
International Conference on Learning Representations (ICLR), 2016
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, 6626-6637, 2017
Self-normalizing neural networks
G Klambauer, T Unterthiner, A Mayr, S Hochreiter
arXiv preprint arXiv:1706.02515, 2017
DeepTox: toxicity prediction using deep learning
A Mayr, G Klambauer, T Unterthiner, S Hochreiter
Frontiers in Environmental Science 3, 80, 2016
GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium.
M Heusel, H Ramsauer, T Unterthiner, B Nessler, G Klambauer, ...
Large-scale comparison of machine learning methods for drug target prediction on ChEMBL
A Mayr, G Klambauer, T Unterthiner, M Steijaert, JK Wegner, ...
Chemical science 9 (24), 5441-5451, 2018
Deep Learning as an Opportunity in Virtual Screening
T Unterthiner, A Mayr, G ünter Klambauer, M Steijaert, J Wenger, ...
Deep Learning and Representation Learning Workshop (NIPS 2014), 2014
Speeding up Semantic Segmentation for Autonomous Driving
M Treml, J Arjona-Medina, T Unterthiner, R Durgesh, F Friedmann, ...
Workshop on Machine Learning for Intelligent Transportation Systems (NIPS 2016), 2016
Toxicity prediction using deep learning
T Unterthiner, A Mayr, G Klambauer, S Hochreiter
arXiv preprint arXiv:1503.01445, 2015
Fréchet ChemNet distance: a metric for generative models for molecules in drug discovery
K Preuer, P Renz, T Unterthiner, S Hochreiter, G Klambauer
Journal of chemical information and modeling 58 (9), 1736-1741, 2018
Using transcriptomics to guide lead optimization in drug discovery projects: Lessons learned from the QSTAR project
B Verbist, G Klambauer, L Vervoort, W Talloen, Z Shkedy, O Thas, ...
Drug discovery today 20 (5), 505-513, 2015
Rudder: Return decomposition for delayed rewards
JA Arjona-Medina, M Gillhofer, M Widrich, T Unterthiner, J Brandstetter, ...
arXiv preprint arXiv:1806.07857, 2018
Coulomb GANs: Provably optimal nash equilibria via potential fields
T Unterthiner, B Nessler, G Klambauer, M Heusel, H Ramsauer, ...
International Conference on Learning Representations (ICLR), 2018
Towards accurate generative models of video: A new metric & challenges
T Unterthiner, S van Steenkiste, K Kurach, R Marinier, M Michalski, ...
arXiv preprint arXiv:1812.01717, 2018
Interpretable deep learning in drug discovery
K Preuer, G Klambauer, F Rippmann, S Hochreiter, T Unterthiner
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 331-345, 2019
DEXUS: identifying differential expression in RNA-Seq studies with unknown conditions
G Klambauer, T Unterthiner, S Hochreiter
Nucleic acids research 41 (21), e198-e198, 2013
Deep Learning for Drug Target Prediction
T Unterthiner, A Mayr, G Klambauer, M Steijaert, H Ceulemans, J Wenger, ...
Workshop on Representation and Learning Methods for Complex Outputs (NIPS2014), 2014
SCIKIT-CUDA 0.5. 1: A Python interface to GPU-powered libraries
LE Givon, T Unterthiner, NB Erichson, DW Chiang, E Larson, L Pfister, ...
An image is worth 16x16 words: Transformers for image recognition at scale
A Dosovitskiy, L Beyer, A Kolesnikov, D Weissenborn, X Zhai, ...
arXiv preprint arXiv:2010.11929, 2020
Rectified factor networks
DA Clevert, A Mayr, T Unterthiner, S Hochreiter
arXiv preprint arXiv:1502.06464, 2015
The system can't perform the operation now. Try again later.
Articles 1–20