most citedThermodynamics-informed graph neural networks

57 citations

8 papers

cs.LO2022

On Robustness for the Skolem, Positivity and Ultimate Positivity Problems

S. Akshay, Hugo Bazille, Blaise Genest +1

The Skolem problem is a long-standing open problem in linear dynamical systems: can a linear recurrence sequence (LRS) ever reach 0 from a given initial configuration? Similarly, t…

cs.LG2022★ 18 cited

Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems

Quercus Hernández, Alberto Badías, Francisco Chinesta +1

We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamic…

cs.GR2022★ 26 cited

Thermodynamics-informed neural networks for physically realistic mixed reality

Quercus Hernández, Alberto Badías, Francisco Chinesta +1

The imminent impact of immersive technologies in society urges for active research in real-time and interactive physics simulation for virtual worlds to be realistic. In this conte…

cond-mat.soft2022★ 12 cited

Local Plastic Response and Slow Heterogeneous Dynamics of Supercooled Liquids

Yan-Wei Li, Yugui Yao, Massimo Pica Ciamarra

We demonstrate, via numerical simulations, that the relaxation dynamics of supercooled liquids correlates well with a plastic length scale measuring a particle's response to impuls…

cond-mat.soft2022★ 12 cited

Interplay between jamming and MIPS in persistent self-propelling particles

Jing Yang, Ran Ni, Massimo Pica Ciamarra

In living and engineered systems of active particles, self-propulsion induces an unjamming transition from a solid to a fluid phase and phase separation between a gas and a liquid-…

cs.LG2022★ 57 cited

Thermodynamics-informed graph neural networks

Quercus Hernández, Alberto Badías, Francisco Chinesta +1

In this paper we present a deep learning method to predict the temporal evolution of dissipative dynamic systems. We propose using both geometric and thermodynamic inductive biases…