Speaker
Dr
Andreas Windisch
(Washington University in St. Louis, JOANNEUM RESEARCH)
Description
Dyson-Schwinger equations (DSEs) are essential tools in quantum field theory for describing particle interactions. Solving these equations in the complex plane presents challenges due to mathematical obstacles like poles and branch cuts. We propose a machine learning approach using deep learning and deep reinforcement learning to automate the detection of these obstacles and adjust integration paths accordingly. This method aims to enhance the efficiency and practicality of solving DSEs, with potential applications in understanding complex physical systems. We outline our approach, discuss initial results, and suggest future steps for this innovative technique.
Primary author
Dr
Andreas Windisch
(Washington University in St. Louis, JOANNEUM RESEARCH)
Co-authors
Dr
Thomas Gallien
(JOANNEUM RESEARCH)
Dr
Christopher Schwarz
