Back to search

University of Southampton

Learning is a Kan Extension

Abstract

dc:description.abstract

This work presents a category-theoretic description of machine learning as Kan extensions of formal theories. Concepts such as databases, machine learning models, model inference, and optimisation algorithms are given mutually compatible interpretations within the language of category theory, contributing a novel perspective and powerful tools to the study of machine learning explainability and design.

Degree

thesis:*
Name dc:type.qualificationname
Ph.D.
Level dc:type.qualificationlevel
doctoral
Grantor dc:publisher.institution
University of Southampton
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Pugh, Matthew
Advisors dc:contributor.advisor
  • Harris, Nicholas
  • Grundy, Jo
  • Cirstea, Corina

Rights

Language dc:language
English, eng

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
University of Southampton
Base URL
eprints.soton.ac.uk/cgi/oai2
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Pugh, Matthew. Learning is a Kan Extension. doctoral thesis, University of Southampton, 2026. https://doi.org/10.5258/SOTON/PG/T276