Zobrazeno 1 - 10
of 111
pro vyhledávání: '"Deisenroth, Marc P."'
Autor:
Paischer, Fabian, Hauzenberger, Lukas, Schmied, Thomas, Alkin, Benedikt, Deisenroth, Marc Peter, Hochreiter, Sepp
Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned on a downstream task for a specific application. The most successful and most commonly used fine-tuning method is to update the pre-trained weights via a low-rank ada
Externí odkaz:
http://arxiv.org/abs/2410.07170
Autor:
Gopakumar, Vignesh, Gray, Ander, Oskarsson, Joel, Zanisi, Lorenzo, Pamela, Stanislas, Giles, Daniel, Kusner, Matt, Deisenroth, Marc Peter
Data-driven surrogate models have shown immense potential as quick, inexpensive approximations to complex numerical and experimental modelling tasks. However, most surrogate models of physical systems do not quantify their uncertainty, rendering thei
Externí odkaz:
http://arxiv.org/abs/2408.09881
Global convolutions have shown increasing promise as powerful general-purpose sequence models. However, training long convolutions is challenging, and kernel parameterizations must be able to learn long-range dependencies without overfitting. This wo
Externí odkaz:
http://arxiv.org/abs/2408.09453
Autor:
Gopakumar, Vignesh, Oskarrson, Joel, Gray, Ander, Zanisi, Lorenzo, Pamela, Stanislas, Giles, Daniel, Kusner, Matt, Deisenroth, Marc
Neural weather models have shown immense potential as inexpensive and accurate alternatives to physics-based models. However, most models trained to perform weather forecasting do not quantify the uncertainty associated with their forecasts. This lim
Externí odkaz:
http://arxiv.org/abs/2406.14483
Human motion generation has paramount importance in computer animation. It is a challenging generative temporal modelling task due to the vast possibilities of human motion, high human sensitivity to motion coherence and the difficulty of accurately
Externí odkaz:
http://arxiv.org/abs/2406.07169
In recent years, machine learning has established itself as a powerful tool for high-resolution weather forecasting. While most current machine learning models focus on deterministic forecasts, accurately capturing the uncertainty in the chaotic weat
Externí odkaz:
http://arxiv.org/abs/2406.04759
Data assimilation is a core component of numerical weather prediction systems. The large quantity of data processed during assimilation requires the computation to be distributed across increasingly many compute nodes, yet existing approaches suffer
Externí odkaz:
http://arxiv.org/abs/2404.12968
Data assimilation (DA) methods use priors arising from differential equations to robustly interpolate and extrapolate data. Popular techniques such as ensemble methods that handle high-dimensional, nonlinear PDE priors focus mostly on state estimatio
Externí odkaz:
http://arxiv.org/abs/2402.17036
Autor:
Gopakumar, Vignesh, Pamela, Stanislas, Zanisi, Lorenzo, Li, Zongyi, Gray, Ander, Brennand, Daniel, Bhatia, Nitesh, Stathopoulos, Gregory, Kusner, Matt, Deisenroth, Marc Peter, Anandkumar, Anima, Team, JOREK, Team, MAST
Publikováno v:
Nucl. Fusion 64 056025 (2024)
Predicting plasma evolution within a Tokamak reactor is crucial to realizing the goal of sustainable fusion. Capabilities in forecasting the spatio-temporal evolution of plasma rapidly and accurately allow us to quickly iterate over design and contro
Externí odkaz:
http://arxiv.org/abs/2311.05967
In recent years, there has been considerable interest in developing machine learning models on graphs to account for topological inductive biases. In particular, recent attention has been given to Gaussian processes on such structures since they can
Externí odkaz:
http://arxiv.org/abs/2311.01198