Topological Effects in Neural Network Field Theory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ferko, Christian, Halverson, James, Jejjala, Vishnu, Robinson, Brandon
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908934291324928
author Ferko, Christian
Halverson, James
Jejjala, Vishnu
Robinson, Brandon
author_facet Ferko, Christian
Halverson, James
Jejjala, Vishnu
Robinson, Brandon
contents Neural network field theory formulates field theory as a statistical ensemble of fields defined by a network architecture and a density on its parameters. We extend the construction to topological settings via the inclusion of discrete parameters that label the topological quantum number. We recover the Berezinskii--Kosterlitz--Thouless transition, including the spin-wave critical line and the proliferation of vortices at high temperatures. We also verify the T-duality of the bosonic string, showing invariance under the exchange of momentum and winding on $S^1$, the transformation of the sigma model couplings according to the Buscher rules on constant toroidal backgrounds, the enhancement of the current algebra at self-dual radius, and non-geometric T-fold transition functions.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02313
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Topological Effects in Neural Network Field Theory
Ferko, Christian
Halverson, James
Jejjala, Vishnu
Robinson, Brandon
High Energy Physics - Theory
Disordered Systems and Neural Networks
Machine Learning
Neural network field theory formulates field theory as a statistical ensemble of fields defined by a network architecture and a density on its parameters. We extend the construction to topological settings via the inclusion of discrete parameters that label the topological quantum number. We recover the Berezinskii--Kosterlitz--Thouless transition, including the spin-wave critical line and the proliferation of vortices at high temperatures. We also verify the T-duality of the bosonic string, showing invariance under the exchange of momentum and winding on $S^1$, the transformation of the sigma model couplings according to the Buscher rules on constant toroidal backgrounds, the enhancement of the current algebra at self-dual radius, and non-geometric T-fold transition functions.
title Topological Effects in Neural Network Field Theory
topic High Energy Physics - Theory
Disordered Systems and Neural Networks
Machine Learning
url https://arxiv.org/abs/2604.02313