A neural network maps ODE states to a slow-evolving latent space with dynamics derived from the original equations via the chain rule, enabling accelerated simulations with fewer function calls.
Physics-informed neural ode (pinode): embedding physics into models using collocation points.Scientific Reports, 13, 06 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accelerating the Simulation of Ordinary Differential Equations Through Physics-Preserving Neural Networks
A neural network maps ODE states to a slow-evolving latent space with dynamics derived from the original equations via the chain rule, enabling accelerated simulations with fewer function calls.