An adaptive sampling algorithm that triangulates the response manifold and adds barycenter points guided by a residual threshold produces surrogate-training data that lowers neural network prediction error versus one-shot samplers in a 1D harmonic transport test case.
A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering design
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An adaptive sampling algorithm for data-generation to build a data-manifold for physical problem surrogate modeling
An adaptive sampling algorithm that triangulates the response manifold and adds barycenter points guided by a residual threshold produces surrogate-training data that lowers neural network prediction error versus one-shot samplers in a 1D harmonic transport test case.