Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by Design

27 May 2021

Papers citing "Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by Design"

10 / 10 papers shown

Title
On Dissipativity of Cross-Entropy Loss in Training ResNets Jens Püttschneider T. Faulwasser 35 0 0 29 May 2024
Port-Hamiltonian Neural ODE Networks on Lie Groups For Robot Dynamics Learning and Control T. Duong Abdullah Altawaitan Jason Stanley Nikolay Atanasov 37 10 0 17 Jan 2024
Physics-Informed Multi-Agent Reinforcement Learning for Distributed Multi-Robot Problems Eduardo Sebastián T. Duong Nikolay Atanasov Eduardo Montijano C. Sagüés 31 3 0 30 Dec 2023
Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations D. Martinelli C. Galimberti I. Manchester Luca Furieri Giancarlo Ferrari-Trecate 25 11 0 06 Apr 2023
Universal Approximation Property of Hamiltonian Deep Neural Networks M. Zakwan M. d’Angelo Giancarlo Ferrari-Trecate 36 5 0 21 Mar 2023
Dynamical systems' based neural networks E. Celledoni Davide Murari B. Owren Carola-Bibiane Schönlieb Ferdia Sherry OOD 46 12 0 05 Oct 2022
LEMURS: Learning Distributed Multi-Robot Interactions Eduardo Sebastián T. Duong Nikolay Atanasov Eduardo Montijano C. Sagüés 76 8 0 20 Sep 2022
Thermodynamics of learning physical phenomena Elías Cueto Francisco Chinesta AI4CE 25 22 0 26 Jul 2022
Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach Luca Furieri C. Galimberti M. Zakwan Giancarlo Ferrari-Trecate 29 20 0 16 Dec 2021
Locally-symplectic neural networks for learning volume-preserving dynamics J. Bajārs 34 9 0 19 Sep 2021