The Weak Penalty Neural ODE uses a weak form loss to filter noise and learn stable chaotic dynamics from noisy observations.
Given an initial conditionu(t 0) =u 0, the evolu- tion of the state is governed by: du(t) dt =f(u(t), t;θ),(5) wherefis a neural network parameterized byθ
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Weak Penalty Neural ODE for Learning Chaotic Dynamics from Noisy Time Series
The Weak Penalty Neural ODE uses a weak form loss to filter noise and learn stable chaotic dynamics from noisy observations.