| Are gans created equal? a large-scale study M Lucic, K Kurach, M Michalski, S Gelly, O Bousquet arXiv preprint arXiv:1711.10337, 2017 | 512 | 2017 |
| Adding gradient noise improves learning for very deep networks A Neelakantan, L Vilnis, QV Le, I Sutskever, L Kaiser, K Kurach, J Martens arXiv preprint arXiv:1511.06807, 2015 | 321 | 2015 |
| Smart reply: Automated response suggestion for email A Kannan, K Kurach, S Ravi, T Kaufmann, A Tomkins, B Miklos, ... Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge …, 2016 | 202 | 2016 |
| Neural random-access machines K Kurach, M Andrychowicz, I Sutskever arXiv preprint arXiv:1511.06392, 2015 | 135 | 2015 |
| The gan landscape: Losses, architectures, regularization, and normalization K Kurach, M Lucic, X Zhai, M Michalski, S Gelly | 99 | 2018 |
| A large-scale study on regularization and normalization in GANs K Kurach, M Lučić, X Zhai, M Michalski, S Gelly International Conference on Machine Learning, 3581-3590, 2019 | 60 | 2019 |
| Learning efficient algorithms with hierarchical attentive memory M Andrychowicz, K Kurach arXiv preprint arXiv:1602.03218, 2016 | 48 | 2016 |
| 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 | 46 | 2018 |
| Are GANs created equal M Lucic, K Kurach, M Michalski, S Gelly, O Bousquet A large-scale study. arXiv e-prints 2 (4), 2017 | 46 | 2017 |
| Learning to discover efficient mathematical identities W Zaremba, K Kurach, R Fergus arXiv preprint arXiv:1406.1584, 2014 | 42 | 2014 |
| Adversarial autoencoders for compact representations of 3D point clouds M Zamorski, M Zięba, P Klukowski, R Nowak, K Kurach, W Stokowiec, ... Computer Vision and Image Understanding 193, 102921, 2020 | 33 | 2020 |
| Google research football: A novel reinforcement learning environment K Kurach, A Raichuk, P Stańczyk, M Zając, O Bachem, L Espeholt, ... Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 4501-4510, 2020 | 27 | 2020 |
| Critical hyper-parameters: No random, no cry O Bousquet, S Gelly, K Kurach, O Teytaud, D Vincent arXiv preprint arXiv:1706.03200, 2017 | 22 | 2017 |
| Adding gradient noise improves learning for very deep networks (2015) A Neelakantan, L Vilnis, QV Le, I Sutskever, L Kaiser, K Kurach, J Martens arXiv preprint arXiv:1511.06807, 0 | 18 | |
| A case for object compositionality in deep generative models of images S van Steenkiste, K Kurach, S Gelly | 12 | 2018 |
| Coalition structure generation with the graphics processing unit K Pawłowski, K Kurach, K Svensson, S Ramchurn, TP Michalak, ... Proceedings of the 2014 international conference on Autonomous agents and …, 2014 | 11 | 2014 |
| Detecting methane outbreaks from time series data with deep neural networks K Pawłowski, K Kurach Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing, 475-484, 2015 | 9 | 2015 |
| Predicting dangerous seismic activity with recurrent neural networks K Kurach, K Pawlowski 2016 Federated Conference on Computer Science and Information Systems …, 2016 | 8 | 2016 |
| Investigating object compositionality in generative adversarial networks S van Steenkiste, K Kurach, J Schmidhuber, S Gelly Neural Networks 130, 309-325, 2020 | 7 | 2020 |
| Systems and methods for estimating message similarity I Krka, I Gilad, K Kurach, A Dai, L Macdermed, PJ Liu, B Miklos, A Damian US Patent 9,774,553, 2017 | 7 | 2017 |
Sylvain GellyGoogle Brain ZurichVerified email at m4x.org
