Revisiting small batch training for deep neural networks D Masters, C Luschi
arXiv preprint arXiv:1804.07612, 2018
1022 2018 Geometric comparison of aerofoil shape parameterization methods DA Masters, NJ Taylor, TCS Rendall, CB Allen, DJ Poole
AIAA journal 55 (5), 1575-1589, 2017
170 2017 Review of aerofoil parameterisation methods for aerodynamic shape optimisation DA Masters, NJ Taylor, T Rendall, CB Allen, DJ Poole
53rd AIAA aerospace sciences meeting, 0761, 2015
65 2015 Influence of shape parameterization on a benchmark aerodynamic optimization problem DA Masters, DJ Poole, NJ Taylor, TCS Rendall, CB Allen
Journal of Aircraft 54 (6), 2242-2256, 2017
38 2017 Impact of shape parameterisation on aerodynamic optimisation of benchmark problem DA Masters, DJ Poole, NJ Taylor, T Rendall, CB Allen
54th AIAA Aerospace Sciences Meeting, 1544, 2016
38 2016 Multilevel subdivision parameterization scheme for aerodynamic shape optimization DA Masters, NJ Taylor, TCS Rendall, CB Allen
AIAA Journal 55 (10), 3288-3303, 2017
32 2017 8-bit numerical formats for deep neural networks B Noune, P Jones, D Justus, D Masters, C Luschi
arXiv preprint arXiv:2206.02915, 2022
23 2022 Proxy-normalizing activations to match batch normalization while removing batch dependence A Labatie, D Masters, Z Eaton-Rosen, C Luschi
Advances in Neural Information Processing Systems 34, 16990-17006, 2021
17 2021 Gps++: An optimised hybrid mpnn/transformer for molecular property prediction D Masters, J Dean, K Klaser, Z Li, S Maddrell-Mander, A Sanders, H Helal, ...
arXiv preprint arXiv:2212.02229, 2022
16 2022 Progressive subdivision curves for aerodynamic shape optimisation DA Masters, NJ Taylor, T Rendall, CB Allen
54th AIAA Aerospace Sciences Meeting, 0559, 2016
16 2016 A locally adaptive subdivision parameterisation scheme for aerodynamic shape optimisation DA Masters, NJ Taylor, T Rendall, CB Allen
34th AIAA Applied Aerodynamics Conference, 3866, 2016
16 2016 Validation of the aerodynamic loading on basic flying disc geometries derived from CFD simulations JR Potts, D Masters
Procedia Engineering 112, 400-405, 2015
12 2015 Making EfficientNet more efficient: Exploring batch-independent normalization, group convolutions and reduced resolution training D Masters, A Labatie, Z Eaton-Rosen, C Luschi
arXiv preprint arXiv:2106.03640, 2021
7 2021 Three-dimensional subdivision parameterisation for aerodynamic shape optimisation DA Masters, NJ Taylor, T Rendall, CB Allen
55th AIAA Aerospace Sciences Meeting, 0036, 2017
6 2017 Towards foundational models for molecular learning on large-scale multi-task datasets D Beaini, S Huang, JA Cunha, G Moisescu-Pareja, O Dymov, ...
arXiv preprint arXiv:2310.04292, 2023
5 2023 GPS++: Reviving the Art of Message Passing for Molecular Property Prediction D Masters, J Dean, K Klaser, Z Li, S Maddrell-Mander, A Sanders, H Helal, ...
arXiv preprint arXiv:2302.02947, 2023
4 2023 Generating QM1B with PySCF A Mathiasen, H Helal, K Klaser, P Balanca, J Dean, C Luschi, D Beaini, ...
Advances in Neural Information Processing Systems 36, 55036-55050, 2023
2 2023 Repurposing density functional theory to suit deep learning A Mathiasen, H Helal, P Balanca, K Klaeser, J Dean, C Luschi, D Beaini, ...
1st Workshop on the Synergy of Scientific and Machine Learning Modeling …, 2023
1 2023 Overflow Event Counter A Alexander, D Masters
US Patent App. 18/483,699, 2024
2024 Processing Device for Intermediate Value Scaling A Alexander, S Knowles, S Felix, C Luschi, B Noune, M Gore, G Da Costa, ...
US Patent App. 18/175,050, 2023
2023