Aspects of Artificial Intelligence: Transforming Machine Learning Systems Naturally

TL;DR

This paper explores the categorical and algebraic structures underlying machine learning systems, highlighting transformations, adjunctions, and universal properties to provide new insights into system design and analysis.

Contribution

It introduces a categorical framework for understanding machine learning systems, emphasizing transformations like quotient, clustering, and Yoneda embedding, and their algebraic properties.

Findings

Categorical relations and transformations elucidate machine learning system structures.

Adjunctions provide optimal problem-solving methods within these systems.

Universal properties and monads reveal new algebraic insights into system behavior.

Abstract

In this paper, we study the machine learning elements which we are interested in together as a machine learning system, consisting of a collection of machine learning elements and a collection of relations between the elements. The relations we concern are algebraic operations, binary relations, and binary relations with composition that can be reasoned categorically. A machine learning system transformation between two systems is a map between the systems, which preserves the relations we concern. The system transformations given by quotient or clustering, representable functor, and Yoneda embedding are highlighted and discussed by machine learning examples. An adjunction between machine learning systems, a special machine learning system transformation loop, provides the optimal way of solving problems. Machine learning system transformations are linked and compared by their maps at 2-cell, natural transformations. New insights and structures can be obtained from universal properties and algebraic structures given by monads, which are generated from adjunctions.