| Dropout as a Bayesian approximation: Representing model uncertainty in deep learning Y Gal, Z Ghahramani Proceedings of the 33rd International Conference on Machine Learning (ICML-16), 2015 | 14818 | 2015 |
| What uncertainties do we need in Bayesian deep learning for computer vision? A Kendall, Y Gal Advances in neural information processing systems, 5574-5584, 2017 | 7401 | 2017 |
| Multi-task learning using uncertainty to weigh losses for scene geometry and semantics A Kendall, Y Gal, R Cipolla Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018 | 4911 | 2018 |
| Deep Bayesian Active Learning with Image Data Y Gal, R Islam, Z Ghahramani International Conference on Machine Learning (ICML), 1183-1192, 2017 | 2443 | 2017 |
| Uncertainty in Deep Learning Y Gal University of Cambridge, 2016 | 2412 | 2016 |
| A theoretically grounded application of dropout in recurrent neural networks Y Gal, Z Ghahramani Advances in neural information processing systems 29, 1019-1027, 2016 | 2243 | 2016 |
| Inferring the effectiveness of government interventions against COVID-19 JM Brauner, S Mindermann, M Sharma, D Johnston, J Salvatier, ... Science 371 (6531), eabd9338, 2021 | 1183 | 2021 |
| Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference Y Gal, Z Ghahramani 4th International Conference on Learning Representations (ICLR) workshop track, 2015 | 1105 | 2015 |
| Detecting hallucinations in large language models using semantic entropy S Farquhar, J Kossen, L Kuhn, Y Gal Nature 630 (8017), 625-630, 2024 | 1009 | 2024 |
| Concrete dropout Y Gal, J Hron, A Kendall Advances in Neural Information Processing Systems, 3581-3590, 2017 | 901 | 2017 |
| AI models collapse when trained on recursively generated data I Shumailov, Z Shumaylov, Y Zhao, N Papernot, R Anderson, Y Gal Nature 631 (8022), 755-759, 2024 | 894 | 2024 |
| BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning A Kirsch, J van Amersfoort, Y Gal Advances in Neural Information Processing Systems, 2019, 2019 | 878 | 2019 |
| Real time image saliency for black box classifiers P Dabkowski, Y Gal Advances in Neural Information Processing Systems, 6967-6976, 2017 | 856 | 2017 |
| Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation L Kuhn, Y Gal, S Farquhar arXiv preprint arXiv:2302.09664, 2023 | 833 | 2023 |
| 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 | 818 | 2021 |
| Uncertainty estimation using a single deep deterministic neural network J van Amersfoort, L Smith, YW Teh, Y Gal International Conference on Machine Learning (ICML), 2020 | 753 | 2020 |
| Learning Invariant Representations for Reinforcement Learning without Reconstruction A Zhang, R McAllister, R Calandra, Y Gal, S Levine International Conference on Learning Representations (ICLR), 2020 | 663 | 2020 |
| The Curse of Recursion: Training on Generated Data Makes Models Forget I Shumailov, Z Shumaylov, Y Zhao, Y Gal, N Papernot, R Anderson arXiv preprint arxiv:2305.17493, 2023 | 546 | 2023 |
| Understanding Measures of Uncertainty for Adversarial Example Detection L Smith, Y Gal Uncertainty in Artificial Intelligence (UAI), 2018 | 500 | 2018 |
| Concrete problems for autonomous vehicle safety: Advantages of Bayesian deep learning R McAllister, Y Gal, A Kendall, M van der Wilk, A Shah, R Cipolla, ... International Joint Conferences on Artificial Intelligence (IJCAI), 2017 | 462* | 2017 |
Zoubin GhahramaniProfessor, University of Cambridge, and VP of Research, Google DeepMindVerified email at eng.cam.ac.uk
