Attention is all you need A Vaswani, N Shazeer, N Parmar, J Uszkoreit, L Jones, AN Gomez, ... Advances in neural information processing systems 30, 2017 | 117168 | 2017 |
Tensor2tensor for neural machine translation A Vaswani, S Bengio, E Brevdo, F Chollet, AN Gomez, S Gouws, L Jones, ... arXiv preprint arXiv:1803.07416, 2018 | 605 | 2018 |
The reversible residual network: Backpropagation without storing activations AN Gomez, M Ren, R Urtasun, RB Grosse Advances in neural information processing systems 30, 2017 | 534 | 2017 |
One model to learn them all L Kaiser, AN Gomez, N Shazeer, A Vaswani, N Parmar, L Jones, ... arXiv preprint arXiv:1706.05137, 2017 | 377 | 2017 |
Disease variant prediction with deep generative models of evolutionary data J Frazer, P Notin, M Dias, A Gomez, JK Min, K Brock, Y Gal, DS Marks Nature 599 (7883), 91-95, 2021 | 367 | 2021 |
Depthwise Separable Convolutions for Neural Machine Translation L Kaiser, AN Gomez, F Chollet International Conference on Learning Representations, 2018 | 341 | 2018 |
A systematic comparison of bayesian deep learning robustness in diabetic retinopathy tasks A Filos, S Farquhar, AN Gomez, TGJ Rudner, Z Kenton, L Smith, ... arXiv preprint arXiv:1912.10481, 2019 | 128* | 2019 |
Learning Sparse Networks Using Targeted Dropout AN Gomez, I Zhang, S Rao Kamalakara, D Madaan, K Swersky, Y Gal, ... arXiv preprint arXiv:1905.13678, 2019 | 115 | 2019 |
Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval P Notin, M Dias, J Frazer, JM Hurtado, AN Gomez, D Marks, Y Gal International Conference on Machine Learning, 16990-17017, 2022 | 114 | 2022 |
The difficulty of training sparse neural networks U Evci, F Pedregosa, A Gomez, E Elsen arXiv preprint arXiv:1906.10732, 2019 | 88 | 2019 |
Self-attention between datapoints: Going beyond individual input-output pairs in deep learning J Kossen, N Band, C Lyle, AN Gomez, T Rainforth, Y Gal Advances in Neural Information Processing Systems 34, 28742-28756, 2021 | 82 | 2021 |
Prioritized training on points that are learnable, worth learning, and not yet learnt S Mindermann, JM Brauner, MT Razzak, M Sharma, A Kirsch, W Xu, ... International Conference on Machine Learning, 15630-15649, 2022 | 81 | 2022 |
Unsupervised cipher cracking using discrete GANs AN Gomez, S Huang, I Zhang, BM Li, M Osama, L Kaiser arXiv preprint arXiv:1801.04883, 2018 | 79 | 2018 |
Targeted dropout AN Gomez, I Zhang, K Swersky, Y Gal, GE Hinton | 33 | 2018 |
Wat zei je? detecting out-of-distribution translations with variational transformers TZ Xiao, AN Gomez, Y Gal arXiv preprint arXiv:2006.08344, 2020 | 32* | 2020 |
Attention-based sequence transduction neural networks NM Shazeer, AN Gomez, LM Kaiser, JD Uszkoreit, LO Jones, NJ Parmar, ... US Patent 10,452,978, 2019 | 31 | 2019 |
Interlocking backpropagation: Improving depthwise model-parallelism AN Gomez, O Key, K Perlin, S Gou, N Frosst, J Dean, Y Gal Journal of Machine Learning Research 23 (171), 1-28, 2022 | 14 | 2022 |
Depthwise separable convolutions for neural machine translation AN Gomez, LM Kaiser, F Chollet US Patent 10,853,590, 2020 | 12 | 2020 |
Robustness to pruning predicts generalization in deep neural networks L Kuhn, C Lyle, AN Gomez, J Rothfuss, Y Gal arXiv preprint arXiv:2103.06002, 2021 | 10 | 2021 |
Multi-task multi-modal machine learning system NM Shazeer, AN Gomez, LM Kaiser, JD Uszkoreit, LO Jones, NJ Parmar, ... US Patent 10,789,427, 2020 | 10 | 2020 |