New Fourier Feature Networks Show Higher Accuracy in Solving PDEs

Researchers have introduced Fourier Feature Networks (FENs), a novel approach for solving partial differential equations. These networks build upon single-hidden-layer neural networks, incorporating Fourier features like cosine and sine to generate basis functions. Similar to Extreme Learning Machines (ELMs), FENs approximate target functions as linear combinations of these bases, but they achieve high precision without needing affine transformations on input variables. Numerical experiments indicate that FENs consistently outperform ELMs in accuracy. AI

IMPACT This research introduces a new neural network architecture that could improve the efficiency and accuracy of solving complex mathematical problems in scientific computing.

RANK_REASON The cluster contains an academic paper detailing a new method for solving partial differential equations. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Extreme Learning Machines
• Fourier Feature Networks
• Partial Differential Equations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →