Advanced search
1 file | 104.21 KB Add to list

Photonic reservoir computing: a new approach to optical information processing

Kristof Vandoorne (UGent) , Martin Fiers (UGent) , David Verstraeten (UGent) , Benjamin Schrauwen (UGent) , Joni Dambre (UGent) and Peter Bienstman (UGent)
Author
Organization
Abstract
Despite ever increasing computational power, recognition and classification problems remain challenging to solve. Recently advances have been made by the introduction of the new concept of reservoir computing. This is a methodology coming from the field of machine learning and neural networks and has been successfully used in several pattern classification problems, like speech and image recognition. The implementations have so far been in software, limiting their speed and power efficiency. Photonics could be an excellent platform for a hardware implementation of this concept because of its inherent parallelism and unique nonlinear behaviour. We propose using a network of coupled Semiconductor Optical Amplifiers (SOA) and show in simulation that it could be used as a reservoir by comparing it on a benchmark speech recognition task to conventional software implementations. In spite of several differences, they perform as good as or better than conventional implementations. Moreover, a photonic implementation offers the promise of massively parallel information processing with low power and high speed. We will also address the role phase plays on the reservoir performance.
Keywords
optical computing, semiconductor optical amplifiers, optical neural nets, speech recognition

Downloads

  • 4540 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 104.21 KB

Citation

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

MLA
Vandoorne, Kristof, et al. “Photonic Reservoir Computing: A New Approach to Optical Information Processing.” Proceedings of SPIE-The International Society for Optical Engineering, vol. 7750, IEEE, 2010, doi:10.1109/ICTON.2010.5548990.
APA
Vandoorne, K., Fiers, M., Verstraeten, D., Schrauwen, B., Dambre, J., & Bienstman, P. (2010). Photonic reservoir computing: a new approach to optical information processing. Proceedings of SPIE-The International Society for Optical Engineering, 7750. https://doi.org/10.1109/ICTON.2010.5548990
Chicago author-date
Vandoorne, Kristof, Martin Fiers, David Verstraeten, Benjamin Schrauwen, Joni Dambre, and Peter Bienstman. 2010. “Photonic Reservoir Computing: A New Approach to Optical Information Processing.” In Proceedings of SPIE-The International Society for Optical Engineering. Vol. 7750. Piscataway, NJ, USA: IEEE. https://doi.org/10.1109/ICTON.2010.5548990.
Chicago author-date (all authors)
Vandoorne, Kristof, Martin Fiers, David Verstraeten, Benjamin Schrauwen, Joni Dambre, and Peter Bienstman. 2010. “Photonic Reservoir Computing: A New Approach to Optical Information Processing.” In Proceedings of SPIE-The International Society for Optical Engineering. Vol. 7750. Piscataway, NJ, USA: IEEE. doi:10.1109/ICTON.2010.5548990.
Vancouver
1.
Vandoorne K, Fiers M, Verstraeten D, Schrauwen B, Dambre J, Bienstman P. Photonic reservoir computing: a new approach to optical information processing. In: Proceedings of SPIE-The International Society for Optical Engineering. Piscataway, NJ, USA: IEEE; 2010.
IEEE
[1]
K. Vandoorne, M. Fiers, D. Verstraeten, B. Schrauwen, J. Dambre, and P. Bienstman, “Photonic reservoir computing: a new approach to optical information processing,” in Proceedings of SPIE-The International Society for Optical Engineering, Munich, Germany, 2010, vol. 7750.
@inproceedings{1155177,
  abstract     = {{Despite ever increasing computational power, recognition and classification problems remain challenging to solve. Recently advances have been made by the introduction of the new concept of reservoir computing. This is a methodology coming from the field of machine learning and neural networks and has been successfully used in several pattern classification problems, like speech and image recognition. The implementations have so far been in software, limiting their speed and power efficiency. Photonics could be an excellent platform for a hardware implementation of this concept because of its inherent parallelism and unique nonlinear behaviour. We propose using a network of coupled Semiconductor Optical Amplifiers (SOA) and show in simulation that it could be used as a reservoir by comparing it on a benchmark speech recognition task to conventional software implementations. In spite of several differences, they perform as good as or better than conventional implementations. Moreover, a photonic implementation offers the promise of massively parallel information processing with low power and high speed. We will also address the role phase plays on the reservoir performance.}},
  articleno    = {{775022}},
  author       = {{Vandoorne, Kristof and Fiers, Martin and Verstraeten, David and Schrauwen, Benjamin and Dambre, Joni and Bienstman, Peter}},
  booktitle    = {{Proceedings of SPIE-The International Society for Optical Engineering}},
  isbn         = {{9781424477975}},
  keywords     = {{optical computing,semiconductor optical amplifiers,optical neural nets,speech recognition}},
  language     = {{eng}},
  location     = {{Munich, Germany}},
  pages        = {{4}},
  publisher    = {{IEEE}},
  title        = {{Photonic reservoir computing: a new approach to optical information processing}},
  url          = {{http://doi.org/10.1109/ICTON.2010.5548990}},
  volume       = {{7750}},
  year         = {{2010}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: