MS-SFNN builds PDE solutions from element-wise products of outputs from d independent fixed-random-weight subnetworks with tunable scaling and cosine activations, then solves coefficients by least squares, claiming superior accuracy on high-frequency problems.
Separated-variable spectral neural networks: A physics-informed learning approach for high-frequency pdes
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
IC gating in adaptive spectral PINNs induces explicit time-dependent gradient scaling that determines relative performance on stiff spring-pendulum ODEs, with exponential gates favored at k=20 and linear gates at k=60.
citing papers explorer
-
Multi-Scale Separable Fourier Neural Networks for Solving High-Frequency PDEs
MS-SFNN builds PDE solutions from element-wise products of outputs from d independent fixed-random-weight subnetworks with tunable scaling and cosine activations, then solves coefficients by least squares, claiming superior accuracy on high-frequency problems.
-
Gradient Scaling Effects in Adaptive Spectral PINNs for Stiff Nonlinear ODEs
IC gating in adaptive spectral PINNs induces explicit time-dependent gradient scaling that determines relative performance on stiff spring-pendulum ODEs, with exponential gates favored at k=20 and linear gates at k=60.