August 20, 2025SciPost Physics CoreOpen Access

Physics-informed neural networks viewpoint for solving the Dyson-Schwinger equations of quantum electrodynamics

View Full Paper

Ask AI

Bookmark

Authors

RTR. C. Terin

Discussion

Member takes

Implication

A novel approach employs physics-informed neural networks to derive fermion mass functions in quantum electrodynamics, suggesting new potential in quantum field theories.

Key Points

The PINNs framework accurately models the fermion's mass function, demonstrating non-perturbative solutions.
By directly embedding integral equations into the loss function, performance improved compared to traditional algorithms.
This analysis employs a distinct neural network approach to develop a continuous representation across momentum spectra.
The implications of this work indicate a shift in machine learning applications within theoretical physics.

Cite This Study

R. C. Terin (2025) studied this question.

synapsesocial.com/papers/68af495fad7bf08b1ead58b2 https://doi.org/10.21468/scipostphyscore.8.3.054

View Full Paper

Ask AI

Bookmark

Implication

A novel approach employs physics-informed neural networks to derive fermion mass functions in quantum electrodynamics, suggesting new potential in quantum field theories.

Physics-informed neural networks viewpoint for solving the Dyson-Schwinger equations of quantum electrodynamics

Discussion

Member takes

Implication

Key Points

Cite This Study

Physics-informed neural networks viewpoint for solving the Dyson-Schwinger equations of quantum electrodynamics

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider