A geometry-aware input layer that feeds networks the logarithmically mapped eigenvalues and eigenvectors of SPD material tensors beats plain MLPs in surrogate modeling of stochastic anisotropic heat conduction.
A review on lightweight materials for defence applications: Present and future de- velopments,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Constitutive Manifold Neural Networks
A geometry-aware input layer that feeds networks the logarithmically mapped eigenvalues and eigenvectors of SPD material tensors beats plain MLPs in surrogate modeling of stochastic anisotropic heat conduction.