**Extraordinario: Notar día, lugar y hora ** KNO-scaling of charged hadron multiplicities within a Machine Learning based approach

Modern developments in Machine Learning methods led us to use these techniques in the field of high-energy physics (HEP) with great benefits. Applications of the artificial intelligence hopefully not only provide solution for so far unsolved questions, but may help to improve physical models by recognizing and investigating the inner correlations from these new approaches. In this contribution state-of-the-art Deep Learning algorithms are utilized to learn non-linear and non-perturbative features of hadron production. The scaling properties of the final state charged hadron and mean jet multiplicity distributions at various LHC energies, calculated by deep residual neural network architectures with different complexities are presented. KNO-scaling properties were adopted by the networks at hadronic level.

Co-author: Gergely Gábor Barnaföldi (Wigner RCP)

[1] G. Bíró, B. Tankó-Bartalis, G.G. Barnaföldi; arXiv:2111.15655
[2] G. Bíró, B. Tankó-Bartalis, G.G. Barnaföldi; PoS ICHEP2022 (2022) 1188; arXiv:2210.10548
[3] G. Bíró, G.G. Barnaföldi; arXiv:2303.05422