Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 1.63 MB
Add to list
  1. Search results
  2. Improving time series recognition and...

Improving time series recognition and prediction with networks and ensembles of passive photonic reservoirs

Matthias Freiberger (UGent) , Stijn Sackesyn (UGent) , Chonghuai Ma, Andrew Katumba (UGent) , Peter Bienstman (UGent) and Joni Dambre (UGent)
(2020) IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS. 26(1).
Author
Organization
Abstract
As the performance increase of traditional Von-Neumann computing attenuates, new approaches to computing need to be found. A promising approach for low-power computing at high bitrates is integrated photonic reservoir computing. In the past though, the feasible reservoir size and computational power of integrated photonic reservoirs have been limited by hardware constraints. An alternative solution to building larger reservoirs is the combination of several small reservoirs to match or exceed the performance of a single bigger one. This paper summarizes our efforts to increase the available computational power by combining multiple reservoirs into a single computing architecture. We investigate several possible combination techniques and evaluate their performance using the classic XOR and header recognition tasks as well as the well-known Santa Fe chaotic laser prediction task. Our findings suggest that a new paradigm of feeding a reservoir's output into the readout structure of the next one shows consistently good results for various tasks as well as for both electrical and optical readouts and coupling schemes.
Keywords
SYSTEMS, Integrated photonic reservoir computing, deep reservoir computing, scalable reservoir computing, unconventional computing, neuro-inspired, computing, neuromorphic computing

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.18 MB
  • Download
    8638399.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 451.35 KB

Citation

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

MLA
Freiberger, Matthias, et al. “Improving Time Series Recognition and Prediction with Networks and Ensembles of Passive Photonic Reservoirs.” IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS, vol. 26, no. 1, 2020, doi:10.1109/JSTQE.2019.2929699.
APA
Freiberger, M., Sackesyn, S., Ma, C., Katumba, A., Bienstman, P., & Dambre, J. (2020). Improving time series recognition and prediction with networks and ensembles of passive photonic reservoirs. IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS, 26(1). https://doi.org/10.1109/JSTQE.2019.2929699
Chicago author-date
Freiberger, Matthias, Stijn Sackesyn, Chonghuai Ma, Andrew Katumba, Peter Bienstman, and Joni Dambre. 2020. “Improving Time Series Recognition and Prediction with Networks and Ensembles of Passive Photonic Reservoirs.” IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS 26 (1). https://doi.org/10.1109/JSTQE.2019.2929699.
Chicago author-date (all authors)
Freiberger, Matthias, Stijn Sackesyn, Chonghuai Ma, Andrew Katumba, Peter Bienstman, and Joni Dambre. 2020. “Improving Time Series Recognition and Prediction with Networks and Ensembles of Passive Photonic Reservoirs.” IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS 26 (1). doi:10.1109/JSTQE.2019.2929699.
Vancouver
1.
Freiberger M, Sackesyn S, Ma C, Katumba A, Bienstman P, Dambre J. Improving time series recognition and prediction with networks and ensembles of passive photonic reservoirs. IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS. 2020;26(1).
IEEE
[1]
M. Freiberger, S. Sackesyn, C. Ma, A. Katumba, P. Bienstman, and J. Dambre, “Improving time series recognition and prediction with networks and ensembles of passive photonic reservoirs,” IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS, vol. 26, no. 1, 2020.
@article{8638399,
  abstract     = {{As the performance increase of traditional Von-Neumann computing attenuates, new approaches to computing need to be found. A promising approach for low-power computing at high bitrates is integrated photonic reservoir computing. In the past though, the feasible reservoir size and computational power of integrated photonic reservoirs have been limited by hardware constraints. An alternative solution to building larger reservoirs is the combination of several small reservoirs to match or exceed the performance of a single bigger one. This paper summarizes our efforts to increase the available computational power by combining multiple reservoirs into a single computing architecture. We investigate several possible combination techniques and evaluate their performance using the classic XOR and header recognition tasks as well as the well-known Santa Fe chaotic laser prediction task. Our findings suggest that a new paradigm of feeding a reservoir's output into the readout structure of the next one shows consistently good results for various tasks as well as for both electrical and optical readouts and coupling schemes.}},
  articleno    = {{7700611}},
  author       = {{Freiberger, Matthias and Sackesyn, Stijn and Ma, Chonghuai and Katumba, Andrew and Bienstman, Peter and Dambre, Joni}},
  issn         = {{1077-260X}},
  journal      = {{IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS}},
  keywords     = {{SYSTEMS,Integrated photonic reservoir computing,deep reservoir computing,scalable reservoir computing,unconventional computing,neuro-inspired,computing,neuromorphic computing}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{11}},
  title        = {{Improving time series recognition and prediction with networks and ensembles of passive photonic reservoirs}},
  url          = {{http://doi.org/10.1109/JSTQE.2019.2929699}},
  volume       = {{26}},
  year         = {{2020}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: