Skip to main content

Thank you for visiting 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.


Generalizing universal function approximators

At the heart of many challenges in scientific research lie complex equations for which no analytical solutions exist. A new neural network model called DeepONet can learn to approximate nonlinear functions as well as operators.

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

Access options

Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: DeepONet translates the theoretically known ability of neural networks to approximate mathematical operators into a working implementation.


  1. Lu, L., Jin, P., Pang, G., Whang, W. & Karniadakis, G. Nat. Mach. Intell. (2021).

  2. Touvron, H., Vedaldi, A., Douze, M. & Jegou, H. In Advances in Neural Information Processing Systems Vol. 32 8252–8262 (NeurIPS, 2019).

  3. Brown, T. et al. In Advances in Neural Information Processing Systems Vol. 33 1877–1901 (NeurIPS, 2020).

  4. Mnih, V. et al. Nature 518, 529–533 (2015).

    Article  Google Scholar 

  5. Silver, D. et al. Nature 529, 484–489 (2016).

    Article  Google Scholar 

  6. Vinyals, O. et al. Nature 575, 350–354 (2019).

    Article  Google Scholar 

  7. Cybenko, G. Math. Control Signals Syst. 2, 303–314 (1989).

    Article  Google Scholar 

  8. Hornik, K., Stinchcombe, M. & White, H. Neural Netw. 2, 359–366 (1989).

    Article  Google Scholar 

  9. Krizhevsky, A., Sutskever, I. & Hinton, G. In Advances in Neural Information Processing Systems Vol. 25 1097–1105 (NeurIPS, 2012).

  10. Chen, T. & Chen, H. IEEE Trans. Neural Netw. 6, 911–917 (1995).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Irina Higgins.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Higgins, I. Generalizing universal function approximators. Nat Mach Intell 3, 192–193 (2021).

Download citation

  • Published:

  • Issue Date:

  • DOI:


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