activity
20202022
most citedThermodynamics-informed graph neural networks

57 citations · 84 across the 6 of their papers we have counts for

collaborators

8 papers

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.CV2022★ 1 cited

A Thermodynamics-informed Active Learning Approach to Perception and Reasoning about Fluids

Beatriz Moya, Alberto Badias, David Gonzalez +2

Learning and reasoning about physical phenomena is still a challenge in robotics development, and computational sciences play a capital role in the search for accurate methods able…

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…

cs.LG2021

Neural Network Layer Algebra: A Framework to Measure Capacity and Compression in Deep Learning

Alberto Badias, Ashis Banerjee

We present a new framework to measure the intrinsic properties of (deep) neural networks. While we focus on convolutional networks, our framework can be extrapolated to any network…

cs.CV2021

Physics perception in sloshing scenes with guaranteed thermodynamic consistency

Beatriz Moya, Alberto Badias, David Gonzalez +2

Physics perception very often faces the problem that only limited data or partial measurements on the scene are available. In this work, we propose a strategy to learn the full sta…

cs.CV2020★ 8 cited

MORPH-DSLAM: Model Order Reduction for PHysics-based Deformable SLAM

Alberto Badias, Iciar Alfaro, David Gonzalez +2

We propose a new methodology to estimate the 3D displacement field of deformable objects from video sequences using standard monocular cameras. We solve in real time the complete (…