A wavelet-basis network trained by least squares solves a range of steady and time-dependent PDEs and captures high-frequency features better than standard PINNs.
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
-
Physics-informed Multiresolution Wavelet Neural Network Method for Solving Partial Differential Equations
A wavelet-basis network trained by least squares solves a range of steady and time-dependent PDEs and captures high-frequency features better than standard PINNs.