
The authors propose a general data-free paradigm where a neural network called LordNet directly learns to solve parametric partial differential equations (PDEs) from the mean squared residual (MSR) loss constructed by the discretized PDE, without requiring any simulated data.


coremsg

lordnet-an-efficient-neural-network-for-learning-to-solve-parametric-partial-differential-equations-without-simulated-data


LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data
