A two-scale neural network architecture with separate state and adjoint networks, rescaled features, and successive training is developed for optimal control of linear convection-dominated PDEs.
Title resolution pending
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
-
Two-scale neural networks for optimal control of linear convection-dominated equations
A two-scale neural network architecture with separate state and adjoint networks, rescaled features, and successive training is developed for optimal control of linear convection-dominated PDEs.