A constraint-preserving autoencoder maps Gaussian mixture parameters to latent space where a single evolution network models transient dynamics across arbitrary initial conditions and system parameters for the Fokker-Planck equation.
Modeling partially ob- served nonlinear dynamical systems and efficient data assimilation via discrete-time con- ditional Gaussian Koopman network.Comput
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.comp-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A deep learning framework for jointly solving transient Fokker-Planck equations with arbitrary parameters and initial distributions
A constraint-preserving autoencoder maps Gaussian mixture parameters to latent space where a single evolution network models transient dynamics across arbitrary initial conditions and system parameters for the Fokker-Planck equation.