Conformal Defects in Neural Network Field Theories
High Energy Physics - Theory
2026-05-18 v2 Machine Learning
Abstract
Neural Network Field Theories (NN-FTs) represent a novel construction of arbitrary field theories, including those of conformal fields, through the specification of the network architecture and prior distribution for the network parameters. In this work, we present a formalism for the construction of conformally invariant defects in these NN-FTs. We demonstrate this new formalism in two toy models of NN scalar field theories. We develop an NN interpretation of an expansion akin to the defect OPE in two-point correlation functions in these models.
Cite
@article{arxiv.2512.07946,
title = {Conformal Defects in Neural Network Field Theories},
author = {Pietro Capuozzo and Brandon Robinson and Benjamin Suzzoni},
journal= {arXiv preprint arXiv:2512.07946},
year = {2026}
}
Comments
23 pages, 1 figure