Learns regionally stable RNN models from input-output data by deriving LMI constraints from generalized sector conditions on deadzone activations and a barrier function to certify forward invariance on a compact set.
2021 European Control Conference (ECC) , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.SY 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A cost-aware space-filling input design method using Gaussian processes for nonlinear system identification that reduces experimental cost while preserving model performance.
citing papers explorer
-
Learning the dynamics of nonlinear systems with regional stability guarantees through linear matrix inequality constraints
Learns regionally stable RNN models from input-output data by deriving LMI constraints from generalized sector conditions on deadzone activations and a barrier function to certify forward invariance on a compact set.
-
Least Costly Space-Filling Experiment Design for the Identification of a Nonlinear System
A cost-aware space-filling input design method using Gaussian processes for nonlinear system identification that reduces experimental cost while preserving model performance.