Characterizing 4-string contact interaction using machine learning - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of High Energy Physics Année : 2024

Characterizing 4-string contact interaction using machine learning

Résumé

The geometry of 4-string contact interaction of closed string feld theory is characterized using machine learning. We obtain Strebel quadratic diferentials on 4-punctured spheres as a neural network by performing unsupervised learning with a custom-built loss function. This allows us to solve for local coordinates and compute their associated mapping radii numerically. We also train a neural network distinguishing vertex from Feynman region. As a check, 4-tachyon contact term in the tachyon potential is computed and a good agreement with the results in the literature is observed. We argue that our algorithm is manifestly independent of number of punctures and scaling it to characterize the geometry of n-string contact interaction is feasible.
Fichier principal
Vignette du fichier
JHEP2024_Article16.pdf (13.07 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03882516 , version 1 (11-04-2024)

Identifiants

Citer

Harold Erbin, Atakan Hilmi Fırat. Characterizing 4-string contact interaction using machine learning. Journal of High Energy Physics, 2024, 2024 (16), pp.1-38. ⟨10.1007/JHEP04(2024)016⟩. ⟨hal-03882516⟩
17 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More