VS-PINN: A fast and efficient training of physics-informed neural networks using variable-scaling methods for solving PDEs with stiff behavior
Seungchan Ko, Sang-Hyeon Park
Topics & Concepts
ScalingArtificial neural networkTraining (meteorology)Variable (mathematics)Applied mathematicsStatistical physicsComputer scienceMathematicsArtificial intelligenceMathematical optimizationAlgorithmPhysicsMathematical analysisGeometryMeteorologyModel Reduction and Neural NetworksFluid Dynamics and Turbulent FlowsProbabilistic and Robust Engineering Design