Data-driven control of echo state-based recurrent neural networks with robust stability guarantees

DOI10.1016/J.SYSCONLE.2024.105974MaRDI QIDQ7029983zbMATH OpenFDO

Authors William D'Amico, Marcello Farina

Publication date 10 February 2025

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

Full work available at URL https://doi.org/10.1016/J.SYSCONLE.2024.105974

zbMATH Keywords

data-based controllinear matrix inequalitiesrecurrent neural networks

Mathematics Subject Classification ID

Sampled-data control/observation systems (93C57) Robust stability (93D09) Input-output approaches in control theory (93D25)

Cites work

• \(l_2\) Induced norm analysis of discrete-time LTI systems for nonnegative input signals and its application to stability analysis of recurrent neural networks
• Direct Nonlinear Control Design: The Virtual Reference Feedback Tuning (VRFT) Approach
• Discrete-time neural network output feedback control of nonlinear discrete-time systems in non-strict form
• Event-triggered neural network control using quadratic constraints for perturbed systems
• Introduction to the Scenario Approach
• Nonlinear MPC design for incrementally ISS systems with application to GRU networks
• On the stability properties of gated recurrent units neural networks
• Re-visiting the echo state property
• Stability Analysis Using Quadratic Constraints for Systems With Neural Network Controllers
• Stability of gated recurrent unit neural networks: convex combination formulation approach
• Virtual reference feedback tuning for linear discrete-time systems with robust stability guarantees based on set membership

This page was built for publication: Data-driven control of echo state-based recurrent neural networks with robust stability guarantees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7029983)