Online calibration of deep learning sub-models for hybrid numerical modeling systems

Abstract Defining end-to-end (or online) training schemes for the calibration of neural sub-models in hybrid systems requires working with an optimization problem that involves the solver of the physical equations. Online learning methodologies thus require the numerical model to be differentiable,...

Full description

Saved in:
Bibliographic Details
Main Authors: Said Ouala, Bertrand Chapron, Fabrice Collard, Lucile Gaultier, Ronan Fablet
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Communications Physics
Online Access:https://doi.org/10.1038/s42005-024-01880-7
Tags: Add Tag
No Tags, Be the first to tag this record!