TRASE-NODEs augment standard NODEs with sensitivity equations to enable data-efficient learning of controlled dynamical systems, showing lower prediction errors than baselines on oscillator and inverter examples.
Trajectory sensitivity analysis of hybrid systems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TRASE-NODEs: Trajectory Sensitivity-aware Neural Ordinary Differential Equations for Efficient Dynamic Modeling
TRASE-NODEs augment standard NODEs with sensitivity equations to enable data-efficient learning of controlled dynamical systems, showing lower prediction errors than baselines on oscillator and inverter examples.