Frequency Shift Physics-Informed Extreme Learning Machine for Solving High-Frequency Partial Differential Equations
arXiv:2607.01694v1 Announce Type: new Abstract: Solving partial differential equations (PDEs) with high-frequency solutions remains a central challenge in physics-informed machine learning due to spectral bias -- the tendency of neural networks to learn low-frequency components preferentially. This paper proposes a Frequency Shift Physics-Informed Extreme Learning Machine (FS-PIELM) framework that addresses this limitation through an additive mechanism for weight initialization. Rather than multiplying random weights by a scaling factor, the method translates the mean of the Gaussian weight di
The continuous drive to improve AI model performance, particularly in scientific computing and physical simulations, necessitates addressing current limitations like spectral bias.
Improving AI's ability to solve high-frequency partial differential equations could significantly accelerate scientific discovery, engineering design, and create more accurate digital twins.
The proposed FS-PIELM framework offers a method to overcome spectral bias in physics-informed machine learning, potentially leading to more robust and accurate AI applications in complex physical systems.
- · Scientific research institutions
- · Engineering and R&D sectors
- · AI/ML researchers
This research directly advances the capability of AI to model complex physical phenomena with higher fidelity.
Improved AI simulation could reduce the need for physical prototypes and accelerate discovery cycles in fields like materials science and drug discovery.
This could lead to a new generation of AI-driven design and optimization tools that dramatically cut development costs and time across industries.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG