| Deep reinforcement learning that matters P Henderson, R Islam, P Bachman, J Pineau, D Precup, D Meger arXiv preprint arXiv:1709.06560, 2017 | 652 | 2017 |
| Learning deep representations by mutual information estimation and maximization RD Hjelm, A Fedorov, S Lavoie-Marchildon, K Grewal, P Bachman, ... arXiv preprint arXiv:1808.06670, 2018 | 360 | 2018 |
| Newsqa: A machine comprehension dataset A Trischler, T Wang, X Yuan, J Harris, A Sordoni, P Bachman, K Suleman arXiv preprint arXiv:1611.09830, 2016 | 308 | 2016 |
| Augmented cyclegan: Learning many-to-many mappings from unpaired data A Almahairi, S Rajeswar, A Sordoni, P Bachman, A Courville arXiv preprint arXiv:1802.10151, 2018 | 175 | 2018 |
| Learning representations by maximizing mutual information across views P Bachman, RD Hjelm, W Buchwalter Advances in Neural Information Processing Systems, 15535-15545, 2019 | 143 | 2019 |
| Learning with pseudo-ensembles P Bachman, O Alsharif, D Precup Advances in neural information processing systems, 3365-3373, 2014 | 141 | 2014 |
| Iterative alternating neural attention for machine reading A Sordoni, P Bachman, A Trischler, Y Bengio arXiv preprint arXiv:1606.02245, 2016 | 100 | 2016 |
| Machine comprehension by text-to-text neural question generation X Yuan, T Wang, C Gulcehre, A Sordoni, P Bachman, S Subramanian, ... arXiv preprint arXiv:1705.02012, 2017 | 90 | 2017 |
| Learning algorithms for active learning P Bachman, A Sordoni, A Trischler arXiv preprint arXiv:1708.00088, 2017 | 81 | 2017 |
| Natural language comprehension with the epireader A Trischler, Z Ye, X Yuan, K Suleman arXiv preprint arXiv:1606.02270, 2016 | 80 | 2016 |
| Calibrating energy-based generative adversarial networks Z Dai, A Almahairi, P Bachman, E Hovy, A Courville arXiv preprint arXiv:1702.01691, 2017 | 70 | 2017 |
| An architecture for deep, hierarchical generative models P Bachman Advances in Neural Information Processing Systems, 4826-4834, 2016 | 43 | 2016 |
| Data generation as sequential decision making P Bachman, D Precup Advances in Neural Information Processing Systems, 3249-3257, 2015 | 41 | 2015 |
| Natural language generation in dialogue using lexicalized and delexicalized data S Sharma, J He, K Suleman, H Schulz, P Bachman arXiv preprint arXiv:1606.03632, 2016 | 20 | 2016 |
| Structure discovery in PPI networks using pattern-based network decomposition P Bachman, Y Liu Bioinformatics 25 (14), 1814-1821, 2009 | 12 | 2009 |
| Variational Generative Stochastic Networks with Collaborative Shaping. P Bachman, D Precup ICML, 1964-1972, 2015 | 11 | 2015 |
| Training deep generative models: Variations on a theme P Bachman, D Precup NIPS Approximate Inference Workshop, 2015 | 10 | 2015 |
| Towards information-seeking agents P Bachman, A Sordoni, A Trischler arXiv preprint arXiv:1612.02605, 2016 | 7 | 2016 |
| Vfunc: a deep generative model for functions P Bachman, R Islam, A Sordoni, Z Ahmed arXiv preprint arXiv:1807.04106, 2018 | 6 | 2018 |
| Improved estimation in time varying models D Precup, P Bachman arXiv preprint arXiv:1206.6385, 2012 | 5* | 2012 |
