Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Machine learning as a tool in theoretical science

Machine learning methods relying on synthetic data are starting to be used in mathematics and theoretical physics. Michael R. Douglas discusses recent advances and ponders on the impact these methods will have in science.

This is a preview of subscription content, access via your institution

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

All prices are NET prices.

References

  1. Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).

    ADS  Article  Google Scholar 

  2. Baek, M. et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 871–876 (2021).

    ADS  Article  Google Scholar 

  3. Tamayo, D. et al. Predicting the long-term stability of compact multiplanet systems. Proc. Natl Acad. Sci. USA 117, 18194–18205 (2020).

    ADS  MathSciNet  Article  Google Scholar 

  4. Davies, A. et al. Advancing mathematics by guiding human intuition with AI. Nature 600, 70–74 (2021).

    ADS  Article  Google Scholar 

  5. Cranmer, M. et al. A Bayesian neural network predicts the dissolution of compact planetary systems. Proc. Natl Acad. Sci. USA 118, e2026053118 (2021).

    Article  Google Scholar 

  6. Carleo, G. et al. Machine learning and the physical sciences. Rev. Mod. Phys. 91, 045002 (2019).

    ADS  Article  Google Scholar 

  7. Davies, A. et al. The signature and cusp geometry of hyperbolic knots. Preprint at https://arxiv.org/abs/2111.15323 (2021).

  8. Mumford, D. in Mathematics: Frontiers and Perspectives (eds Arnold, V. et al.) 197–218 (AMS, 2000).

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Michael R. Douglas.

Ethics declarations

Competing interests

The author declares no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Douglas, M.R. Machine learning as a tool in theoretical science. Nat Rev Phys 4, 145–146 (2022). https://doi.org/10.1038/s42254-022-00431-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42254-022-00431-9

This article is cited by

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing