(K)not machine learning

TL;DR

This paper reviews recent machine learning approaches to understanding relations between knot invariants, connecting mathematical physics and data-driven methods to derive new analytical insights.

Contribution

It introduces a novel perspective on applying machine learning to knot theory and gauge theories, aiming to translate Big Data experiments into analytic results.

Findings

Machine learning models reveal relations between knot invariants.

Connections established between knot invariants and physical theories.

Potential for deriving new analytical results from data-driven approaches.

Abstract

We review recent efforts to machine learn relations between knot invariants. Because these knot invariants have meaning in physics, we explore aspects of Chern-Simons theory and higher dimensional gauge theories. The goal of this work is to translate numerical experiments with Big Data to new analytic results.