| Dropout: a simple way to prevent neural networks from overfitting N Srivastava, G Hinton, A Krizhevsky, I Sutskever, R Salakhutdinov The journal of machine learning research 15 (1), 1929-1958, 2014 | 53964 | 2014 |
| Reducing the dimensionality of data with neural networks GE Hinton, RR Salakhutdinov science 313 (5786), 504-507, 2006 | 23927 | 2006 |
| Show, attend and tell: Neural image caption generation with visual attention K Xu, J Ba, R Kiros, K Cho, A Courville, R Salakhutdinov, RS Zemel, ... International Conference on Machine Learning (ICML) 2 (3), 5, 2015 | 12968 | 2015 |
| Improving neural networks by preventing co-adaptation of feature detectors GE Hinton arXiv preprint arXiv:1207.0580, 2012 | 11724 | 2012 |
| XLNet: Generalized Autoregressive Pretraining for Language Understanding Z Yang arXiv preprint arXiv:1906.08237, 2019 | 10349 | 2019 |
| Probabilistic matrix factorization R Salakhutdinov, A Mnih Neural Information Processing Systems 21, 2007 | 5596* | 2007 |
| Siamese neural networks for one-shot image recognition G Koch, R Zemel, R Salakhutdinov ICML deep learning workshop 2 (1), 1-30, 2015 | 5526 | 2015 |
| Transformer-xl: Attentive language models beyond a fixed-length context Z Dai arXiv preprint arXiv:1901.02860, 2019 | 4480 | 2019 |
| Human-level concept learning through probabilistic program induction BM Lake, R Salakhutdinov, JB Tenenbaum Science 350 (6266), 1332-1338, 2015 | 3718 | 2015 |
| Deep Boltzmann Machines. R Salakhutdinov, GE Hinton International Conference on Artificial Intelligence and Statistics (AISTATS …, 2009 | 3498* | 2009 |
| Unsupervised learning of video representations using lstms N Srivastava, E Mansimov, R Salakhutdinov International Conference on Machine Learning (ICML) 2, 2015 | 3339 | 2015 |
| Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books Y Zhu arXiv preprint arXiv:1506.06724, 2015 | 3292 | 2015 |
| Skip-thought vectors R Kiros, Y Zhu, RR Salakhutdinov, R Zemel, R Urtasun, A Torralba, ... Advances in neural information processing systems 28, 2015 | 3205 | 2015 |
| Neighbourhood components analysis J Goldberger, GE Hinton, S Roweis, RR Salakhutdinov Advances in neural information processing systems 17, 2004 | 2967 | 2004 |
| Deep sets M Zaheer, S Kottur, S Ravanbakhsh, B Poczos, RR Salakhutdinov, ... Advances in neural information processing systems 30, 2017 | 2948 | 2017 |
| Hubert: Self-supervised speech representation learning by masked prediction of hidden units WN Hsu, B Bolte, YHH Tsai, K Lakhotia, R Salakhutdinov, A Mohamed IEEE/ACM transactions on audio, speech, and language processing 29, 3451-3460, 2021 | 2718 | 2021 |
| Restricted Boltzmann machines for collaborative filtering R Salakhutdinov, A Mnih, G Hinton Proceedings of the 24th international conference on Machine learning, 791-798, 2007 | 2664 | 2007 |
| Unifying visual-semantic embeddings with multimodal neural language models R Kiros, R Salakhutdinov, RS Zemel Transactions of the Association for Computational Linguistics (TACL), 2014 | 2412* | 2014 |
| Revisiting Semi-Supervised Learning with Graph Embeddings Z Yang, W Cohen, R Salakhutdinov International Conference on Machine Learning (ICML), 2016 | 2364 | 2016 |
| HotpotQA: A dataset for diverse, explainable multi-hop question answering Z Yang, P Qi, S Zhang, Y Bengio, WW Cohen, R Salakhutdinov, ... arXiv preprint arXiv:1809.09600, 2018 | 2190 | 2018 |
Geoffrey HintonEmeritus Prof. Computer Science, University of Toronto在 cs.toronto.edu 的电子邮件经过验证