127 citations · 327 across the 4 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.CE2020★ 96 cited
Deep learning of thermodynamics-aware reduced-order models from data
Quercus Hernandez, Alberto Badias, David Gonzalez +2
We present an algorithm to learn the relevant latent variables of a large-scale discretized physical system and predict its time evolution using thermodynamically-consistent deep n…
cs.LG2020★ 89 cited
Structure-preserving neural networks
Quercus Hernández, Alberto Badias, David Gonzalez +2
We develop a method to learn physical systems from data that employs feedforward neural networks and whose predictions comply with the first and second principles of thermodynamics…