Category theory in machine learning: rewriting models for time series
Category theory in machine learning: rewriting models for time series
In this project, we give a categorical perspective on the class of dynamical system models in machine learning, where processes are iteratively applied over time. We develop an algebraic description of these models as a measure of compositionality: the properties of a model that are preserved under composition.
Iolo Jones, Jerry Swan, & Jeffrey Giansiracusa. Algebraic Dynamical Systems in Machine Learning. Appl Categor Struct 32, 4 (2024). https://doi.org/10.1007/s10485-023-09762-9