PU-GKAN applies Shepard normalization to Gaussian bases in KANs, yielding exact constant reproduction, reduced epsilon sensitivity, and better validation accuracy across tested regimes.
Physics-informedkanpointnet:Deep learning for simultaneous solutions to inverse problems in incom- pressible flow on numerous irregular geometries
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A stable operating interval for the Gaussian scale parameter ε in KANs is ε ∈ [1/(G-1), 2/(G-1)], derived from first-layer feature geometry and validated across multiple approximation and physics-informed problems.
LNN-PINN integrates liquid residual blocks into PINNs and reports lower RMSE and MAE on four benchmark problems while leaving the original physics modeling and optimization pipeline unchanged.
citing papers explorer
-
Partition-of-Unity Gaussian Kolmogorov-Arnold Networks
PU-GKAN applies Shepard normalization to Gaussian bases in KANs, yielding exact constant reproduction, reduced epsilon sensitivity, and better validation accuracy across tested regimes.
-
Scale-Parameter Selection in Gaussian Kolmogorov-Arnold Networks
A stable operating interval for the Gaussian scale parameter ε in KANs is ε ∈ [1/(G-1), 2/(G-1)], derived from first-layer feature geometry and validated across multiple approximation and physics-informed problems.
-
LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks
LNN-PINN integrates liquid residual blocks into PINNs and reports lower RMSE and MAE on four benchmark problems while leaving the original physics modeling and optimization pipeline unchanged.