Paper Image

Algebraic term rewriting for machine learning models

Published on:

6 November 2023

Primary Category:

Category Theory

Paper Authors:

Iolo Jones,

Jerry Swan,

Jeffrey Giansiracusa

Bullets

Key Details

Presents algebraic term rewriting as a model for machine learning

Shows it captures structure and dynamics of models like RNNs

Allows constraints and compositionality to be described algebraically

Proves it embeds dynamical systems and is compositional

AI generated summary

Algebraic term rewriting for machine learning models

This paper introduces a formal framework to represent machine learning models, especially dynamical systems like RNNs, as algebraic term rewriting systems. This allows structural constraints and compositional properties to be described algebraically. The main results show this framework captures dynamical systems, and properties are preserved compositionally.

Answers from this paper

Comments

No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up