ASRNNs recover Hamiltonian dynamics and symbolic equations from trajectories with only two irregularly spaced noisy points by preserving symplectic structure without derivative estimation.
We propose ASRNNs (Adaptable Symplectic Recurrent Neural Networks) which combine parameter-cognizant Hamiltonian learning with symplectic recurrence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Machine Learning Hamiltonian Dynamical Systems with Sparse and Noisy Data
ASRNNs recover Hamiltonian dynamics and symbolic equations from trajectories with only two irregularly spaced noisy points by preserving symplectic structure without derivative estimation.