On the stability properties of gated recurrent units neural networks

DOI10.1016/j.sysconle.2021.105049zbMath1482.93521arXiv2011.06806OpenAlexW3102807666MaRDI QIDQ2059489

Fabio Bonassi, Marcello Farina, Riccardo Scattolini

Publication date: 14 December 2021

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.06806

zbMATH Keywords

neural networksinput-to-state stabilityincremental input-to-state stabilitygated recurrent units

Mathematics Subject Classification ID

Input-output approaches in control theory (93D25) Networked control (93B70)

Related Items (3)

Recurrent neural network-based internal model control design for stable nonlinear systems ⋮ Robust constrained nonlinear model predictive control with gated recurrent unit model ⋮ Robust offset‐free nonlinear model predictive control for systems learned by neural nonlinear autoregressive exogenous models

Cites Work

• Unnamed Item
• Moving-horizon state estimation for nonlinear discrete-time systems: new stability results and approximation schemes
• Neural networks for control systems - a survey
• Recurrent neural network-based model predictive control for continuous pharmaceutical manufacturing
• Multilayer feedforward networks are universal approximators
• Global asymptotic stability and stabilization of long short-term memory neural networks with constant weights and biases
• A Lyapunov approach to incremental stability properties
• Input-to-state stability for discrete-time nonlinear systems

This page was built for publication: On the stability properties of gated recurrent units neural networks