| Understanding measures of uncertainty for adversarial example detection L Smith, Y Gal arXiv preprint arXiv:1803.08533, 2018 | 273 | 2018 |
| Uncertainty estimation using a single deep deterministic neural network J Van Amersfoort, L Smith, YW Teh, Y Gal International conference on machine learning, 9690-9700, 2020 | 268 | 2020 |
| Galaxy Zoo: probabilistic morphology through Bayesian CNNs and active learning M Walmsley, L Smith, C Lintott, Y Gal, S Bamford, H Dickinson, L Fortson, ... Monthly Notices of the Royal Astronomical Society 491 (2), 1554-1574, 2020 | 101 | 2020 |
| 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 | 76 | 2019 |
| Galaxy Zoo DECaLS: Detailed visual morphology measurements from volunteers and deep learning for 314 000 galaxies M Walmsley, C Lintott, T Géron, S Kruk, C Krawczyk, KW Willett, ... Monthly Notices of the Royal Astronomical Society 509 (3), 3966-3988, 2022 | 49 | 2022 |
| Towards global flood mapping onboard low cost satellites with machine learning G Mateo-Garcia, J Veitch-Michaelis, L Smith, SV Oprea, G Schumann, ... Scientific reports 11 (1), 1-12, 2021 | 49 | 2021 |
| Amphiphilic π-Allyliridium C,O-Benzoates Enable Regio- and Enantioselective Amination of Branched Allylic Acetates Bearing Linear Alkyl Groups AT Meza, T Wurm, L Smith, SW Kim, JR Zbieg, CE Stivala, MJ Krische Journal of the American Chemical Society 140 (4), 1275-1279, 2018 | 45 | 2018 |
| On feature collapse and deep kernel learning for single forward pass uncertainty J van Amersfoort, L Smith, A Jesson, O Key, Y Gal arXiv preprint arXiv:2102.11409, 2021 | 42 | 2021 |
| Sufficient conditions for idealised models to have no adversarial examples: a theoretical and empirical study with bayesian neural networks Y Gal, L Smith arXiv preprint arXiv:1806.00667, 2018 | 35 | 2018 |
| Improving deterministic uncertainty estimation in deep learning for classification and regression J van Amersfoort, L Smith, A Jesson, O Key, Y Gal arXiv preprint arXiv:2102.11409 2 (3), 4, 2021 | 34 | 2021 |
| Liberty or depth: Deep bayesian neural nets do not need complex weight posterior approximations S Farquhar, L Smith, Y Gal Advances in Neural Information Processing Systems 33, 4346-4357, 2020 | 34 | 2020 |
| Benchmarking Bayesian deep learning with diabetic retinopathy diagnosis A Filos, S Farquhar, AN Gomez, TGJ Rudner, Z Kenton, L Smith, ... Preprint at https://arxiv. org/abs/1912.10481, 2019 | 18 | 2019 |
| Uncertainty quantification for virtual diagnostic of particle accelerators O Convery, L Smith, Y Gal, A Hanuka Physical Review Accelerators and Beams 24 (7), 074602, 2021 | 11 | 2021 |
| Idealised bayesian neural networks cannot have adversarial examples: Theoretical and empirical study Y Gal, L Smith arXiv preprint arXiv:1806.00667, 2018 | 7 | 2018 |
| Try depth instead of weight correlations: Mean-field is a less restrictive assumption for deeper networks S Farquhar, L Smith, Y Gal arXiv preprint arXiv:2002.03704, 2020 | 5 | 2020 |
| Flood detection on low cost orbital hardware G Mateo-Garcia, S Oprea, L Smith, J Veitch-Michaelis, G Schumann, ... arXiv preprint arXiv:1910.03019, 2019 | 5 | 2019 |
| Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective L Smith, J van Amersfoort, H Huang, S Roberts, Y Gal arXiv preprint arXiv:2106.02469, 2021 | 4 | 2021 |
| Capsule Networks--A Probabilistic Perspective L Smith, L Schut, Y Gal, M van der Wilk arXiv preprint arXiv:2004.03553, 2020 | 4 | 2020 |
| Try depth instead of weight correlations: Mean field is a less restrictive assumption for variational inference in deep networks S Farquhar, L Smith, Y Gal Bayesian Deep Learning Workshop At NeurIPS, 2020 | 4 | 2020 |
| An example of HSE's assessment of major hazards as an aid to planning control by local authorities MF Pantony, LM Smith Institution of Chemical Engineers symposium series, 377-395, 1982 | 3 | 1982 |
Yarin GalAssociate Professor, University of OxfordVerified email at cs.ox.ac.uk
