FE-MAD is an end-to-end differentiable FEM framework that learns polyconvex and interpretable constitutive neural networks for incompressible hyperelasticity directly from DIC and heterogeneous experimental data.
Abdolazizi, Roland C
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
CONDITIONAL 2representative citing papers
Input-convex networks learn thermodynamically admissible internal energy and dissipation potentials for isotropic thermoelasticity from temperature and deformation data without entropy measurements.
citing papers explorer
-
Finite Element-Based Material Learning via Automatic Differentiation: Learning constitutive neural network models from full-field deformation data
FE-MAD is an end-to-end differentiable FEM framework that learns polyconvex and interpretable constitutive neural networks for incompressible hyperelasticity directly from DIC and heterogeneous experimental data.
-
A Convex Route to Thermoelasticity: Learning Internal Energy and Dissipation
Input-convex networks learn thermodynamically admissible internal energy and dissipation potentials for isotropic thermoelasticity from temperature and deformation data without entropy measurements.