NEFEM uses neural networks as adaptive enrichment functions inside the SGFEM framework, trained via the Ritz functional, to achieve better approximation with fewer degrees of freedom for problems with strong oscillations or weak interface discontinuities.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural enrichment finite element method: A hybrid framework for problems with strong oscillations or interface problems
NEFEM uses neural networks as adaptive enrichment functions inside the SGFEM framework, trained via the Ritz functional, to achieve better approximation with fewer degrees of freedom for problems with strong oscillations or weak interface discontinuities.