Advancing mathematics by guiding human intuition with AI

This repo contains two colab notebooks which accompany the paper, available online at https://www.nature.com/articles/s41586-021-04086-x

Both the representation theory and knot theory colabs retrain an ML model from scratch and recreate our published results by our same intermediary steps.

Installation

No installation is required; the notebook files can be opened on the Colab site from a copy of these files uploaded from a local machine, saved in google drive or directly from this github repo. Alternatively they can be accessed via these links:

• Knot theory - https://colab.sandbox.google.com/github/deepmind/mathematics_conjectures/blob/main/knot_theory.ipynb
• Representation theory - https://colab.sandbox.google.com/github/deepmind/mathematics_conjectures/blob/main/representation_theory.ipynb

Usage

Once the notebook has loaded, simply follow the comments along and execute all of the cells from top to bottom.

Citing this work

Please cite https://www.nature.com/articles/s41586-021-04086-x

Disclaimer

This is not an official Google product.

Data

Pre-trained weights and all data are licensed under licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ or send a letter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.