1

Audited surrogate gradients for efficient model-based flow control
Feedback controllers for fluid flows are expensive to design, since each candidate must be evaluated by numerically solving the …
Ruige Kong, Stefania Fresca
PDF
GraphEP: A calibrated data system and benchmark for learning cardiac electrophysiology
High-fidelity simulations can produce complete scientific data at spatiotemporal resolutions that are difficult to obtain …
Matteo Baldan, Chiara D'Ercoli, James Rowbottom, Pietro Lio, Stefania Fresca
Integrating Fourier neural operators with diffusion models to improve spectral representation of synthetic earthquake ground motion response
Nuclear reactor buildings must be designed to withstand the dynamic load induced by strong ground motion earthquakes. For this reason, …
Niccolo Perrone, Fanny Lehmann, Hugo Gabrielidis, Stefania Fresca, Filippo Gatti
PDF
Beyond Interpolation: Extrapolative reasoning with reinforcement learning and graph neural networks
Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, …
Niccolo Grillo, Andrea Toccaceli, Benjamin Estermann, Joël Mathys, Stefania Fresca, Roger Wattenhofer
PDF
Neural latent dynamics models
We introduce Neural Latent Dynamics Models (NLDMs), a neural ordinary differential equations (ODEs)-based architecture to perform …
Nicola Farenga, Stefania Fresca, Andrea Manzoni
PDF
Deep learning-based reduced order models in cardiac electrophysiology
The numerical simulation of multiple scenarios for cardiac electrophysiology (EP) problems easily becomes computationally prohibitive …
Stefania Fresca, Andrea Manzoni, Luca Dede', Alfio Quarteroni
PDF
Long-time prediction of nonlinear parametrized dynamical systems by deep learning-based ROMs
Deep learning-based reduced order models (DL-ROMs) have been recently proposed to overcome common limitations shared by conventional …
Federico Fatone, Stefania Fresca, Andrea Manzoni
PDF