Advanced search
1 file | 274.38 KB

Reservoir computing using a delayed feedback system: towards photonic implementations

Author
Organization
Abstract
Delayed feedback systems are known to exhibit a rich dynamical behavior, showing a wide variety of dynamical regimes. We use this richness to implement reservoir computing, a processing concept in machine learning. In this paper we demonstrate the proof of principle on an electronic system, however the approach is readily transferable to photonics, promising fast and computationally efficient all-optical processing. Using only one single node with delayed feedback instead of an entire network of nodes, we succeed in obtaining state-of-the-art results on benchmarks such as spoken digit recognition and system identification.
Keywords
photonic, opto-electronic, reservoir computing, delayed feedback

Downloads

  • Appeltant.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 274.38 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Appeltant, Lennert, MC Soriano, Guy Van der Sande, Jan Dankaert, Serge Massar, Joni Dambre, Benjamin Schrauwen, Claudio R Mirasso, and Ingo Fisher. 2011. “Reservoir Computing Using a Delayed Feedback System: Towards Photonic Implementations.” In Proceedings Annual Symposium of the IEEE/LEOS Benelux Chapter, 2008, 125–128. IEEE/LEOS.
APA
Appeltant, Lennert, Soriano, M., Van der Sande, G., Dankaert, J., Massar, S., Dambre, J., Schrauwen, B., et al. (2011). Reservoir computing using a delayed feedback system: towards photonic implementations. Proceedings Annual Symposium of the IEEE/LEOS Benelux Chapter, 2008 (pp. 125–128). Presented at the 16th Annual Symposium of the IEEE Photonics Benelux Chapter, IEEE/LEOS.
Vancouver
1.
Appeltant L, Soriano M, Van der Sande G, Dankaert J, Massar S, Dambre J, et al. Reservoir computing using a delayed feedback system: towards photonic implementations. Proceedings Annual Symposium of the IEEE/LEOS Benelux Chapter, 2008. IEEE/LEOS; 2011. p. 125–8.
MLA
Appeltant, Lennert, MC Soriano, Guy Van der Sande, et al. “Reservoir Computing Using a Delayed Feedback System: Towards Photonic Implementations.” Proceedings Annual Symposium of the IEEE/LEOS Benelux Chapter, 2008. IEEE/LEOS, 2011. 125–128. Print.
@inproceedings{2057639,
  abstract     = {Delayed feedback systems are known to exhibit a rich dynamical behavior, showing a wide variety of dynamical regimes. We use this richness to implement reservoir computing, a processing concept in machine learning. In this paper we demonstrate the proof of principle on an electronic system, however the approach is readily transferable to photonics, promising fast and computationally efficient all-optical processing. Using only one single node with delayed feedback instead of an entire network of nodes, we succeed in obtaining state-of-the-art results on benchmarks such as spoken digit recognition and system identification.},
  author       = {Appeltant, Lennert and Soriano, MC and Van der Sande, Guy and Dankaert, Jan and Massar, Serge and Dambre, Joni and Schrauwen, Benjamin and Mirasso, Claudio R and Fisher, Ingo},
  booktitle    = {Proceedings Annual Symposium of the IEEE/LEOS Benelux Chapter, 2008},
  language     = {eng},
  location     = {Ghent, Belgium},
  pages        = {125--128},
  publisher    = {IEEE/LEOS},
  title        = {Reservoir computing using a delayed feedback system: towards photonic implementations},
  year         = {2011},
}