K-HOrderDNN approximates univariate KST components with high-order networks, reducing basis count from (p+1)^d to about d(p+1) and showing strong accuracy on high-frequency, high-dimensional PDE tests.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Kolmogorov High Order Deep Neural Network for High Frequency Partial Differential Equations in High Dimensions
K-HOrderDNN approximates univariate KST components with high-order networks, reducing basis count from (p+1)^d to about d(p+1) and showing strong accuracy on high-frequency, high-dimensional PDE tests.