Are gans created equal? a large-scale study M Lucic, K Kurach, M Michalski, S Gelly, O Bousquet Advances in neural information processing systems 31, 2018 | 1270 | 2018 |
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 | 622 | 2015 |
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 | 539 | 2018 |
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 | 412 | 2020 |
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 | 393 | 2016 |
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 | 214 | 2019 |
Neural random-access machines K Kurach, M Andrychowicz, I Sutskever arXiv preprint arXiv:1511.06392, 2015 | 195 | 2015 |
The gan landscape: Losses, architectures, regularization, and normalization K Kurach, M Lucic, X Zhai, M Michalski, S Gelly | 164 | 2018 |
FVD: A new metric for video generation T Unterthiner, S van Steenkiste, K Kurach, R Marinier, M Michalski, ... | 135 | 2019 |
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 | 112 | 2020 |
Are GANs created equal M Lucic, K Kurach, M Michalski, S Gelly, O Bousquet A large-scale study. arXiv e-prints 2 (4), 2017 | 82 | 2017 |
Learning to discover efficient mathematical identities W Zaremba, K Kurach, R Fergus Advances in Neural Information Processing Systems 27, 2014 | 68 | 2014 |
Learning efficient algorithms with hierarchical attentive memory M Andrychowicz, K Kurach arXiv preprint arXiv:1602.03218, 2016 | 53 | 2016 |
Investigating object compositionality in generative adversarial networks S Van Steenkiste, K Kurach, J Schmidhuber, S Gelly Neural Networks 130, 309-325, 2020 | 46 | 2020 |
Critical hyper-parameters: No random, no cry O Bousquet, S Gelly, K Kurach, O Teytaud, D Vincent arXiv preprint arXiv:1706.03200, 2017 | 43 | 2017 |
Adding gradient noise improves learning for very deep networks. arXiv 2015 A Neelakantan, L Vilnis, QV Le, I Sutskever, L Kaiser, K Kurach, J Martens arXiv preprint arXiv:1511.06807, 2020 | 28 | 2020 |
A case for object compositionality in deep generative models of images S van Steenkiste, K Kurach, S Gelly | 18 | 2018 |
Predicting dangerous seismic activity with recurrent neural networks K Kurach, K Pawlowski 2016 Federated Conference on Computer Science and Information Systems …, 2016 | 14 | 2016 |
Coalition structure generation with the graphics processing unit K Pawłowski, K Kurach, K Svensson, S Ramchurn, TP Michalak, ... Proc. AAMAS, 293-300, 2014 | 14 | 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: 15th …, 2015 | 13 | 2015 |