Neural networks solve complex physics equations for Yang-Mills theory

Researchers have developed a novel neural network approach to solve complex Dyson-Schwinger equations (DSEs) in four-dimensional Landau-gauge Yang--Mills theory. The neural solutions closely match traditional fixed-point solutions, demonstrating stability across various network configurations and boundary conditions. This method successfully reproduces key physical phenomena, including the MiniMOM ultraviolet running and the sign change of the gluon Schwinger function, within the constraints of the employed truncation. AI

IMPACT This research demonstrates a novel application of neural networks in solving fundamental physics problems, potentially opening new avenues for computational physics research.

RANK_REASON The item describes a scientific paper detailing a new method for solving complex physics equations using neural networks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• CatalyzeX
• DagsHub
• Dyson--Schwinger equations
• Gotit.pub
• Hugging Face
• IArxiv
• MiniMOM
• Rodrigo Carmo Terin
• ScienceCast
• Yang--Mills

• paper
• other

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