no code implementations • 18 Oct 2023 • Nicola Rares Franco, Daniel Fraulin, Andrea Manzoni, Paolo Zunino
Deep Learning is having a remarkable impact on the design of Reduced Order Models (ROMs) for Partial Differential Equations (PDEs), where it is exploited as a powerful tool for tackling complex problems for which classical methods might fail.
no code implementations • 10 Mar 2021 • Nicola R. Franco, Andrea Manzoni, Paolo Zunino
Our work is based on the use of deep autoencoders, which we employ for encoding and decoding a high fidelity approximation of the solution manifold.
no code implementations • 23 Feb 2021 • Michela C. Massi, Nicola R. Franco, Francesca Ieva, Andrea Manzoni, Anna Maria Paganoni, Paolo Zunino
The algorithm relies on an interaction learning step based on a well-known frequent item set mining algorithm, and a novel dissimilarity-based interaction selection step that allows the user to specify the number of interactions to be included in the LR model.
no code implementations • modeling and scientific computing 2007 • Alexandre Ern, Annette F. Stephansen, Paolo Zunino
We consider Discontinuous Galerkin approximations of advection-diffusion equations with anisotropic and discontinuous diffusivity, and propose the symmetric weighted interior penalty (SWIP) method for better coping with locally vanishing diffusivity.