% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Bacchetta:623193,
author = {Bacchetta, Alessandro and Bertone, Valerio and Bissolotti,
Chiara and Cerutti, Matteo and Radici, Marco and Rodini,
Simone and Rossi, Lorenzo},
collaboration = {{MAP Collaboration}},
title = {{A} {N}eural-{N}etwork {E}xtraction of{U}npolarised
{T}ransverse-{M}omentum-{D}ependent {D}istributions},
reportid = {PUBDB-2025-00641, DESY-25-022. JLAB-THY-25-4221.
arXiv:2502.04166},
year = {2025},
abstract = {We present the first extraction from experimental Drell-Yan
data of unpolarised transverse-momentum-dependent
distributions using neural networks to parametrise their
nonperturbativepart. We show that neural networks outperform
traditional parametrisations achieving a betterdescription
of data. This work not only establishes the feasibility of
using neural networks to ex-plore the multi-dimensional
partonic structure of hadrons, but also paves the way to
more accuratedeterminations which exploit machine-learning
techniques.},
cin = {T},
cid = {I:(DE-H253)T-20120731},
pnm = {611 - Fundamental Particles and Forces (POF4-611) / DFG
project G:(GEPRIS)409651613 - FOR 2926: Next Generation
Perturbative QCD for Hadron Structure: Preparing for the
Electron-Ion Collider (409651613) / DFG project
G:(GEPRIS)430915355 - Multi-Parton Wechselwirkungen und
Beiträge mit höherem Twist (430915355)},
pid = {G:(DE-HGF)POF4-611 / G:(GEPRIS)409651613 /
G:(GEPRIS)430915355},
experiment = {EXP:(DE-MLZ)NOSPEC-20140101},
typ = {PUB:(DE-HGF)25},
eprint = {2502.04166},
howpublished = {arXiv:2502.04166},
archivePrefix = {arXiv},
SLACcitation = {$\%\%CITATION$ = $arXiv:2502.04166;\%\%$},
doi = {10.3204/PUBDB-2025-00641},
url = {https://bib-pubdb1.desy.de/record/623193},
}