Thermodynamics of learning physical phenomena
E Cueto, F Chinesta - Archives of Computational Methods in Engineering, 2023 - Springer
Thermodynamics could be seen as an expression of physics at a high epistemic level. As
such, its potential as an inductive bias to help machine learning procedures attain accurate …
such, its potential as an inductive bias to help machine learning procedures attain accurate …
Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems
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 …
on the port-Hamiltonian formalism. To satisfy by construction the principles of …
Hamiltonian deep neural networks guaranteeing nonvanishing gradients by design
Deep neural networks (DNNs) training can be difficult due to vanishing and exploding
gradients during weight optimization through backpropagation. To address this problem, we …
gradients during weight optimization through backpropagation. To address this problem, we …
Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach
Large-scale cyber-physical systems require that control policies are distributed, that is, that
they only rely on local real-time measurements and communication with neighboring agents …
they only rely on local real-time measurements and communication with neighboring agents …
An embedded Hamiltonian dynamic evolutionary neural network model for high-dimensional data recognition
K Qian, L Tian - Applied Soft Computing, 2023 - Elsevier
Aiming at the limitation of Hamiltonian neural network in high-dimensional data processing
with non-observable physical quantity system, an embedded Hamiltonian dynamic …
with non-observable physical quantity system, an embedded Hamiltonian dynamic …
Structure-Preserving Deep Learning
QM Hernández Laín, E Cueto Prendes… - zaguan.unizar.es
Las tecnologías de simulación se han convertido en una herramienta útil para modelizar
muchos sistemas en una amplia variedad de disciplinas, desde las ciencias sociales a las …
muchos sistemas en una amplia variedad de disciplinas, desde las ciencias sociales a las …