Is deep learning a useful tool for the pure mathematician?

2023/04/25 by Geordie Williamson, Williamson, Geordie · 4 citations
Computer Science · Neuroscience · #Algebraic Geometry (math.AG) #Cognitive Science and Education Research #Cognitive Science and Mapping #Combinatorics (math.CO) #Computability, Logic, AI Algorithms #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Representation Theory (math.RT)

paper · pdf · doi:10.48550/arxiv.2304.12602

openalex publication_date 2023/04/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A personal and informal account of what a pure mathematician might expect when using tools from deep learning in their research.

Cited by

• How to Use Deep Learning to Identify Sufficient Conditions: A Case Study on Stanley's e-Positivity
• Murmurations: a case study in AI-assisted mathematics
• A Hybrid Framework for Healing Semigroups with Machine Learning
• Explaining Deep Network Classification of Matrices: A Case Study on Monotonicity

Related

• Deep Learning: An Introduction for Applied Mathematicians
• The many faces of deep learning
• Mathematical theory of deep learning
• Deep Learning and Mathematical Intuition: A Review of (Davies et al. 2021)
• Why Does Deep and Cheap Learning Work So Well?