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.

RESERVOIR COMPUTING

Predicting hidden structure in dynamical systems

The dynamical properties of a nonlinear system can be learned from its time-series data, but is it possible to predict what happens when the system is tuned far away from its training values?

This is a preview of subscription content

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

All prices are NET prices.

Fig. 1: A reservoir computer is trained on time-series data of a dynamical system — such as a fox–rabbit predator–prey system — below a bifurcation point.

References

  1. 1.

    Lukoševičius, M. & Jaeger, H. Comp. Sci. Rev. 3, 127–149 (2009).

    Article  Google Scholar 

  2. 2.

    Rodan, A. & Tino, P. IEEE Trans. Neural Netw. 22, 131–144 (2011).

    Article  Google Scholar 

  3. 3.

    Appeltant, L. et al. Nat. Commun. 2, 468 (2011).

    Article  Google Scholar 

  4. 4.

    Tanaka, G. et al. Neural Netw. 115, 100–123 (2019).

    Article  Google Scholar 

  5. 5.

    Kim, J. Z., Lu, Z., Nozari, E., Pappas, G. J. & Bassett, D. S. Nat. Mach. Intell. https://doi.org/10.1038/s42256-021-00321-2 (2021).

  6. 6.

    Lu, Z., Hunt, B. R. & Ott, E. Chaos 28, 061104 (2018).

    MathSciNet  Article  Google Scholar 

  7. 7.

    Klos, C., Kossio, Y. F. K., Goedeke, S., Gilra, A. & Memmesheimer, R.-M. Phys. Rev. Lett. 125, 088103 (2020).

    Article  Google Scholar 

  8. 8.

    Feldkamp, L. A., Puskorius, G. V. & Moore, P. C. Info. Sci. 98, 217–235 (1997).

    Article  Google Scholar 

  9. 9.

    Ferrell, J. E. Jr. Curr. Biol. 22, R458–R466 (2012).

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Daniel J. Gauthier.

Ethics declarations

Competing interests

D.J.G. is a co-founder of ResCon Technologies, LLC, which focuses on commercializing reservoir computers for edge computing applications.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Gauthier, D.J., Fischer, I. Predicting hidden structure in dynamical systems. Nat Mach Intell 3, 281–282 (2021). https://doi.org/10.1038/s42256-021-00329-8

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-021-00329-8

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