ICODE, a control-affine neural ODE that feeds external inputs directly into the dynamics, predicts trajectories better than NODE, ANODE, and CDE on simulated physical benchmarks, but its contraction guarantee is not enforced or verified.
Stable neural ODE with Lyapunov-stable equilibrium points for defending against adversarial attacks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ICODE: Modeling Dynamical Systems with Extrinsic Input Information
ICODE, a control-affine neural ODE that feeds external inputs directly into the dynamics, predicts trajectories better than NODE, ANODE, and CDE on simulated physical benchmarks, but its contraction guarantee is not enforced or verified.