Computing with a camera

Photonic computing devices are a compelling alternative to conventional computing setups for machine learning applications, as they are nonlinear, fast and easy to parallelize. Recent work demonstrates the potential of these optical systems to process and classify human motion from video.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: The reservoir computing setup of Antonik and colleagues.


  1. 1.

    Antonik, P., Marsal, N., Brunner, D. & Rontani, D. Nat. Mach. Intell. https://doi.org/10.1038/s42256-019-0110-8 (2019).

  2. 2.

    Jaeger, H. The “Echo State” Approach to Analysing and Training Recurrent Neural Networks (GMD, 2001).

  3. 3.

    Maass, W., Natschläger, T. & Markram, H. Neural Comp. 14, 2531–2560 (2002).

  4. 4.

    Fernando, C. & Sojakka, S. in Advances in Artificial Life 588–597 (Springer, 2003).

  5. 5.

    Dockendorf, K. P., Park, I., He, P., Príncipe, J. C. & DeMarse, T. B. Biosystems 95, 90–97 (2009).

  6. 6.

    Bueno, J. et al. Optica 5, 756–760 (2018).

  7. 7.

    Van der Sande, G., Brunner, D. & Soriano, M. C. Nanophotonics 6, 561 (2017).

  8. 8.

    Shastri, B. J. et al. in Encyclopedia of Complexity and Systems Science (ed. Meyers, R. A.) 702 (Springer, 2018).

  9. 9.

    Shen, Y. et al. Nat. Photon. 11, 441–446 (2017).

Download references

Author information

Correspondence to Kathy Lüdge.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Lüdge, K., Röhm, A. Computing with a camera. Nat Mach Intell 1, 551–552 (2019). https://doi.org/10.1038/s42256-019-0124-2

Download citation