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

TL;DR

This paper introduces high-precision phase-shift transferable neural networks designed to improve high-frequency function approximation and PDE solving in scientific computing.

Contribution

The paper proposes a novel neural network architecture that enhances high-frequency approximation and transferability for PDE solutions.

Findings

Achieves higher accuracy in high-frequency function approximation.

Demonstrates improved PDE solving capabilities.

Outperforms existing neural network methods in relevant benchmarks.

Abstract

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.