LSA-PINN: Linear Boundary Connectivity Loss for Solving PDEs on Complex Geometry
LSA-PINN: Linear Boundary Connectivity Loss for Solving PDEs on Complex Geometry
We present a novel loss formulation for efficient learning of complex dynamics from governing physics, typically described by partial differential equations (PDEs), using physics-informed neural networks (PINNs). In our experiments, existing versions of PINNs are seen to learn poorly in many problems, especially for complex geometries, as it becomes increasingly …