High-Precision Phase-Shift Transferable Neural Networks for High-Frequency Function Approximation and PDE Solution

Neural network based methods have emerged as a promising paradigm for scientific computing, yet they face critical bottlenecks in high frequency function approximation and partial differential equation (PDE) solving. --- Source: arXiv:2604.03186v1 - http://arxiv.org/abs/2604.03186v1 PDF: https://arxiv.org/pdf/2604.03186v1 Original Link: http://arxiv.org/abs/2604.03186v1