Recurrent equilibrium networks: flexible dynamic models with guaranteed stability and robustness

DOI10.1109/TAC.2023.3294101MaRDI QIDQ6588564zbMATH OpenFDO

Authors Max Revay, Ruigang Wang, Ian R. Manchester

Publication date 16 August 2024

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

Full work available at URL https://doi.org/10.1109/TAC.2023.3294101

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computational methods for problems pertaining to systems and control theory (93-08) System identification (93B30) Estimation and detection in stochastic control theory (93E10)

Cited in

(6)

• On dissipativity of cross-entropy loss in training ResNets. A turnpike towards architecture search
• Model updating for nonlinear systems with stability guarantees
• Convex equilibrium-free stability and performance analysis of discrete-time nonlinear systems
• Output contraction analysis of discrete-time nonlinear systems with an application to RNNs
• LipKernel: Lipschitz-bounded convolutional neural networks via dissipative layers
• Provably robust data-driven sensor fault diagnosis using incrementally stable recurrent equilibrium networks

This page was built for publication: Recurrent equilibrium networks: flexible dynamic models with guaranteed stability and robustness

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6588564)