| Fitnets: Hints for thin deep nets A Romero, N Ballas, SE Kahou, A Chassang, C Gatta, Y Bengio arXiv preprint arXiv:1412.6550, 2014 | 2356 | 2014 |
| Describing Videos by Exploiting Temporal Structure L Yao, A Torabi, K Cho, N Ballas, C Pal, H Larochelle, A Courville arXiv preprint arXiv:1502.08029, 2015 | 1120 | 2015 |
| Theano: A Python framework for fast computation of mathematical expressions R Al-Rfou, G Alain, A Almahairi, C Angermueller, D Bahdanau, N Ballas, ... arXiv e-prints, arXiv: 1605.02688, 2016 | 984* | 2016 |
| A closer look at memorization in deep networks D Arpit, S Jastrzębski, N Ballas, D Krueger, E Bengio, MS Kanwal, ... International conference on machine learning, 233-242, 2017 | 967 | 2017 |
| Delving deeper into convolutional networks for learning video representations N Ballas, L Yao, C Pal, A Courville arXiv preprint arXiv:1511.06432, 2015 | 549 | 2015 |
| Recurrent batch normalization T Cooijmans, N Ballas, C Laurent, Ç Gülçehre, A Courville arXiv preprint arXiv:1603.09025, 2016 | 415 | 2016 |
| Three factors influencing minima in sgd S Jastrzębski, Z Kenton, D Arpit, N Ballas, A Fischer, Y Bengio, A Storkey arXiv preprint arXiv:1711.04623, 2017 | 322 | 2017 |
| Zoneout: Regularizing rnns by randomly preserving hidden activations D Krueger, T Maharaj, J Kramár, M Pezeshki, N Ballas, NR Ke, A Goyal, ... arXiv preprint arXiv:1606.01305, 2016 | 308 | 2016 |
| Stochastic gradient push for distributed deep learning M Assran, N Loizou, N Ballas, M Rabbat International Conference on Machine Learning, 344-353, 2019 | 196 | 2019 |
| A dissection of overfitting and generalization in continuous reinforcement learning A Zhang, N Ballas, J Pineau arXiv preprint arXiv:1806.07937, 2018 | 129 | 2018 |
| Improved conditional vrnns for video prediction L Castrejon, N Ballas, A Courville Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019 | 90 | 2019 |
| Dynamic capacity networks A Almahairi, N Ballas, T Cooijmans, Y Zheng, H Larochelle, A Courville International Conference on Machine Learning, 2549-2558, 2016 | 83 | 2016 |
| SlowMo: Improving communication-efficient distributed SGD with slow momentum J Wang, V Tantia, N Ballas, M Rabbat arXiv preprint arXiv:1910.00643, 2019 | 81 | 2019 |
| Residual connections encourage iterative inference S Jastrzębski, D Arpit, N Ballas, V Verma, T Che, Y Bengio arXiv preprint arXiv:1710.04773, 2017 | 74 | 2017 |
| A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering T Maharaj, N Ballas, A Rohrbach, A Courville, C Pal Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2017 | 69 | 2017 |
| Fast approximate natural gradient descent in a kronecker factored eigenbasis T George, C Laurent, X Bouthillier, N Ballas, P Vincent Advances in Neural Information Processing Systems 31, 2018 | 65 | 2018 |
| On the relation between the sharpest directions of DNN loss and the SGD step length S Jastrzębski, Z Kenton, N Ballas, A Fischer, Y Bengio, A Storkey arXiv preprint arXiv:1807.05031, 2018 | 62* | 2018 |
| Deep nets don't learn via memorization D Krueger, N Ballas, S Jastrzebski, D Arpit, MS Kanwal, T Maharaj, ... | 56 | 2017 |
| Space-time robust representation for action recognition N Ballas, Y Yang, ZZ Lan, B Delezoide, F Preteux, A Hauptmann Proceedings of the IEEE International Conference on Computer Vision, 2704-2711, 2013 | 49 | 2013 |
| Large-scale image mining with flickr groups AL Ginsca, A Popescu, HL Borgne, N Ballas, P Vo, I Kanellos International Conference on Multimedia Modeling, 318-334, 2015 | 34 | 2015 |
Yoshua BengioProfessor of computer science, University of Montreal, Mila, IVADO, CIFARVerified email at umontreal.ca
