A PINN framework with separate networks for conductivity and potentials, multiscale wavelet excitations, and FFE recovers dominant conductivity structures from finite DtN data with 3-12% relative error on synthetic tests, with FFE aiding sharp features.
Neural-network meth- ods for boundary value problems with irregular boundaries
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Holomorphic neural networks enforce exact satisfaction of harmonic PDEs for 3D Laplace and elasticity problems using Whittaker representations and boundary-only training.
PINNs for first-order plane-strain elastodynamics achieve higher accuracy with soft boundary enforcement over implicit geometries but require longer training than hard enforcement.
citing papers explorer
-
Recovering Sharp Conductivity Features in the Finite-Data Calder\'on Problem with Physics-Informed Neural Networks
A PINN framework with separate networks for conductivity and potentials, multiscale wavelet excitations, and FFE recovers dominant conductivity structures from finite DtN data with 3-12% relative error on synthetic tests, with FFE aiding sharp features.
-
A holomorphic neural network framework for 3D boundary value problems governed by harmonic potentials
Holomorphic neural networks enforce exact satisfaction of harmonic PDEs for 3D Laplace and elasticity problems using Whittaker representations and boundary-only training.
-
Exact Boundary Enforcement Along Implicit Geometries for Physics-Informed, Deep Learning Problems in Continuum Mechanics
PINNs for first-order plane-strain elastodynamics achieve higher accuracy with soft boundary enforcement over implicit geometries but require longer training than hard enforcement.