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.
Itskov, Tensor Algebra and Tensor Analysis for Engineers: With Applications to Continuum Mechanics
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
background 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.