Contraction-based LMI conditions on learned neural ODE models guarantee convergence of unknown nonlinear systems to a neighborhood of their equilibrium.
Thi s property makes the single-hidden layer NN ( k = 1) commonly used for system representation in control theory [11], [22] , [29]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural network based control of unknown nonlinear systems via contraction analysis
Contraction-based LMI conditions on learned neural ODE models guarantee convergence of unknown nonlinear systems to a neighborhood of their equilibrium.