Saved in:
Bibliographic Details
Main Author: van Nierop, Leo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.14543
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915071128502272
author van Nierop, Leo
author_facet van Nierop, Leo
contents In particle physics, the fundamental forces are subject to symmetries called gauge invariance. It is a redundancy in the mathematical description of any physical system. In this article I will demonstrate that the transformer architecture exhibits the same properties, and show that the default representation of transformers has partially, but not fully removed the gauge invariance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14543
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transformer models are gauge invariant: A mathematical connection between AI and particle physics
van Nierop, Leo
Machine Learning
High Energy Physics - Theory
In particle physics, the fundamental forces are subject to symmetries called gauge invariance. It is a redundancy in the mathematical description of any physical system. In this article I will demonstrate that the transformer architecture exhibits the same properties, and show that the default representation of transformers has partially, but not fully removed the gauge invariance.
title Transformer models are gauge invariant: A mathematical connection between AI and particle physics
topic Machine Learning
High Energy Physics - Theory
url https://arxiv.org/abs/2412.14543