Electromagnetic and weak structure of the nucleon studied within Bayesian neural network methods | AI for Physics

Our project focused on developing Bayesian neural network methods for studying the nucleon’s electroweak structure. This approach reduced the dependence of the analysis on model assumptions and enabled a more reliable extraction of physical observables. The work led to new parametrizations of electromagnetic and axial form factors, studies of two-photon exchange effects, comparisons with quantum field-theoretical calculations, and a Bayesian determination of the proton charge radius.

Beyond the scientific publications, the project also led to the development of a dedicated BNN C++ library, written from scratch by K. Graczyk and C. Juszczak.

Funding:Polish Ministry of Science Grant, Project No. N N202 368439

References:
JHEP 09, 053 (2010)
Phys. Rev. C 84, 034314 (2011)
Phys. Rev. C 88, 065205 (2013)
Phys. Rev. C 90, 054334 (2014)
J. Phys. G 42, 034019 (2015)
PoS NuFACT2018 (2019) 101
Phys. Rev. C 99, 025204 (2019)

Collaborators: Cezary Juszczak, Robert Sulej, Piotr Płoński, Luis Alvarez-Ruso, Eduardo Saul-Sal