Hamiltonian Deep Neural Networks Guaranteeing Nonvanishing Gradients by Design

DOI10.1109/tac.2023.3239430OpenAlexW3165062653MaRDI QIDQ6056086

Unnamed Author, Liang Xu, Luca Furieri, Ferrari-Trecate, Giancarlo

Publication date: 29 September 2023

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tac.2023.3239430

zbMATH Keywords

Hamiltonian systemsdeep neural networks (DNNs)ordinary differential equations (ODE) discretization

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Related Items (1)

Dynamical Systems–Based Neural Networks

This page was built for publication: Hamiltonian Deep Neural Networks Guaranteeing Nonvanishing Gradients by Design