Aspects of Artificial Intelligence: Transforming Machine Learning Systems Naturally
This work provides a theoretical foundation for analyzing machine learning systems using category theory, which is incremental in applying existing mathematical concepts to this domain.
The paper tackles the problem of understanding machine learning systems through a categorical framework, focusing on transformations that preserve algebraic and relational structures, and highlights adjunctions as optimal problem-solving mechanisms.
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.