no code implementations • 21 May 2024 • James Requeima, John Bronskill, Dami Choi, Richard E. Turner, David Duvenaud
Machine learning practitioners often face significant challenges in formally integrating their prior knowledge and beliefs into predictive models, limiting the potential for nuanced and context-aware analyses.
no code implementations • 30 Mar 2024 • Anna Vaughan, Stratis Markou, Will Tebbutt, James Requeima, Wessel P. Bruinsma, Tom R. Andersson, Michael Herzog, Nicholas D. Lane, J. Scott Hosking, Richard E. Turner
Machine learning is revolutionising medium-range weather prediction.
no code implementations • 16 Nov 2023 • Lorenzo Bonito, James Requeima, Aliaksandra Shysheya, Richard E. Turner
Over the last few years, Neural Processes have become a useful modelling tool in many application areas, such as healthcare and climate sciences, in which data are scarce and prediction uncertainty estimates are indispensable.
1 code implementation • 30 Oct 2023 • Jonas Scholz, Tom R. Andersson, Anna Vaughan, James Requeima, Richard E. Turner
On held-out weather stations, Sim2Real training substantially outperforms the same model architecture trained only with reanalysis data or only with station data, showing that reanalysis data can serve as a stepping stone for learning from real observations.
1 code implementation • 18 Nov 2022 • Tom R. Andersson, Wessel P. Bruinsma, Stratis Markou, James Requeima, Alejandro Coca-Castro, Anna Vaughan, Anna-Louise Ellis, Matthew A. Lazzara, Dani Jones, J. Scott Hosking, Richard E. Turner
This paper proposes using a convolutional Gaussian neural process (ConvGNP) to address these issues.
no code implementations • 7 Jul 2022 • Ambrish Rawat, James Requeima, Wessel Bruinsma, Richard Turner
Machine unlearning refers to the task of removing a subset of training data, thereby removing its contributions to a trained model.
no code implementations • 16 Mar 2022 • Stratis Markou, James Requeima, Wessel P. Bruinsma, Anna Vaughan, Richard E. Turner
Existing approaches which model output dependencies, such as Neural Processes (NPs; Garnelo et al., 2018b) or the FullConvGNP (Bruinsma et al., 2021), are either complicated to train or prohibitively expensive.
no code implementations • ICLR 2022 • Stratis Markou, James Requeima, Wessel Bruinsma, Anna Vaughan, Richard E Turner
Existing approaches which model output dependencies, such as Neural Processes (NPs; Garnelo et al., 2018) or the FullConvGNP (Bruinsma et al., 2021), are either complicated to train or prohibitively expensive.
no code implementations • 22 Aug 2021 • Stratis Markou, James Requeima, Wessel Bruinsma, Richard Turner
Conditional Neural Processes (CNP; Garnelo et al., 2018) are an attractive family of meta-learning models which produce well-calibrated predictions, enable fast inference at test time, and are trainable via a simple maximum likelihood procedure.
1 code implementation • pproximateinference AABI Symposium 2021 • Wessel P. Bruinsma, James Requeima, Andrew Y. K. Foong, Jonathan Gordon, Richard E. Turner
Neural Processes (NPs; Garnelo et al., 2018a, b) are a rich class of models for meta-learning that map data sets directly to predictive stochastic processes.
2 code implementations • NeurIPS 2020 • Andrew Y. K. Foong, Wessel P. Bruinsma, Jonathan Gordon, Yann Dubois, James Requeima, Richard E. Turner
Stationary stochastic processes (SPs) are a key component of many probabilistic models, such as those for off-the-grid spatio-temporal data.
2 code implementations • ICML 2020 • John Bronskill, Jonathan Gordon, James Requeima, Sebastian Nowozin, Richard E. Turner
Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines.
3 code implementations • ICLR 2020 • Jonathan Gordon, Wessel P. Bruinsma, Andrew Y. K. Foong, James Requeima, Yann Dubois, Richard E. Turner
We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data.
1 code implementation • NeurIPS 2019 • James Requeima, Jonathan Gordon, John Bronskill, Sebastian Nowozin, Richard E. Turner
We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and establish connections to the meta-learning and few-shot learning literature.
Ranked #6 on Few-Shot Image Classification on Meta-Dataset Rank
1 code implementation • 20 Feb 2018 • James Requeima, Will Tebbutt, Wessel Bruinsma, Richard E. Turner
Multi-output regression models must exploit dependencies between outputs to maximise predictive performance.
no code implementations • ICML 2017 • José Miguel Hernández-Lobato, James Requeima, Edward O. Pyzer-Knapp, Alán Aspuru-Guzik
These results show that PDTS is a successful solution for large-scale parallel BO.