Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Bouabid, Shahine"'
Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e.g., optimising the average-case risk, worst-case risk, or interpolations t
Externí odkaz:
http://arxiv.org/abs/2404.04669
Emulators, or reduced complexity climate models, are surrogate Earth system models that produce projections of key climate quantities with minimal computational resources. Using time-series modelling or more advanced machine learning techniques, data
Externí odkaz:
http://arxiv.org/abs/2307.10052
A directed acyclic graph (DAG) provides valuable prior knowledge that is often discarded in regression tasks in machine learning. We show that the independences arising from the presence of collider structures in DAGs provide meaningful inductive bia
Externí odkaz:
http://arxiv.org/abs/2301.11214
Autor:
Bouabid, Shahine, Watson-Parris, Duncan, Stefanović, Sofija, Nenes, Athanasios, Sejdinovic, Dino
Aerosol-cloud interactions constitute the largest source of uncertainty in assessments of the anthropogenic climate change. This uncertainty arises in part from the difficulty in measuring the vertical distributions of aerosols, and only sporadic ver
Externí odkaz:
http://arxiv.org/abs/2205.04296
Autor:
Bouabid, Shahine1 (AUTHOR) shahine.bouabid@stats.ox.ac.uk, Sejdinovic, Dino2 (AUTHOR), Watson‐Parris, Duncan3 (AUTHOR)
Publikováno v:
Journal of Advances in Modeling Earth Systems. Jun2024, Vol. 16 Issue 6, p1-53. 53p.
Refining low-resolution (LR) spatial fields with high-resolution (HR) information, often known as statistical downscaling, is challenging as the diversity of spatial datasets often prevents direct matching of observations. Yet, when LR samples are mo
Externí odkaz:
http://arxiv.org/abs/2105.12909
Autor:
Harder, Paula, Jones, William, Lguensat, Redouane, Bouabid, Shahine, Fulton, James, Quesada-Chacón, Dánell, Marcolongo, Aris, Stefanović, Sofija, Rao, Yuhan, Manshausen, Peter, Watson-Parris, Duncan
The recent explosion in applications of machine learning to satellite imagery often rely on visible images and therefore suffer from a lack of data during the night. The gap can be filled by employing available infra-red observations to generate visi
Externí odkaz:
http://arxiv.org/abs/2011.07017
Public satellite missions are commonly bound to a trade-off between spatial and temporal resolution as no single sensor provides fine-grained acquisitions with frequent coverage. This hinders their potential to assist vegetation monitoring or humanit
Externí odkaz:
http://arxiv.org/abs/2011.04762
Autor:
Bouabid, Shahine, Delaitre, Vincent
Mixup - a neural network regularization technique based on linear interpolation of labeled sample pairs - has stood out by its capacity to improve model's robustness and generalizability through a surprisingly simple formalism. However, its extension
Externí odkaz:
http://arxiv.org/abs/2003.02065