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, log in via an institution to check access.
References
Lu, L., Jin, P., Pang, G., Whang, W. & Karniadakis, G. Nat. Mach. Intell. https://doi.org/10.1038/s42256-021-00302-5 (2021).
Touvron, H., Vedaldi, A., Douze, M. & Jegou, H. In Advances in Neural Information Processing Systems Vol. 32 8252–8262 (NeurIPS, 2019).
Brown, T. et al. In Advances in Neural Information Processing Systems Vol. 33 1877–1901 (NeurIPS, 2020).
Mnih, V. et al. Nature 518, 529–533 (2015).
Silver, D. et al. Nature 529, 484–489 (2016).
Vinyals, O. et al. Nature 575, 350–354 (2019).
Cybenko, G. Math. Control Signals Syst. 2, 303–314 (1989).
Hornik, K., Stinchcombe, M. & White, H. Neural Netw. 2, 359–366 (1989).
Krizhevsky, A., Sutskever, I. & Hinton, G. In Advances in Neural Information Processing Systems Vol. 25 1097–1105 (NeurIPS, 2012).
Chen, T. & Chen, H. IEEE Trans. Neural Netw. 6, 911–917 (1995).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Higgins, I. Generalizing universal function approximators. Nat Mach Intell 3, 192–193 (2021). https://doi.org/10.1038/s42256-021-00318-x
Published:
Issue Date:
DOI: https://doi.org/10.1038/s42256-021-00318-x
- Springer Nature Limited