Integrated photonic reservoir computing with an all-optical readout
- Author
- Chonghuai Ma, Joris Van Kerrebrouck (UGent) , Hong Deng (UGent) , Stijn Sackesyn (UGent) , Emmanuel Gooskens (UGent) , Bing Bai, Joni Dambre (UGent) and Peter Bienstman (UGent)
- Organization
- Project
- Abstract
- Integrated photonic reservoir computing has been demonstrated to be able to tackle different problems because of its neural network nature. A key advantage of photonic reservoir computing over other neuromorphic paradigms is its straightforward readout system, which facilitates both rapid training and robust, fabrication variation-insensitive photonic integrated hardware implementation for real-time processing. We present our recent development of a fully-optical, coherent photonic reservoir chip integrated with an optical readout system, capitalizing on these benefits. Alongside the integrated system, we also demonstrate a weight update strategy that is suitable for the integrated optical readout hardware. Using this online training scheme, we successfully solved 3-bit header recognition and delayed XOR tasks at 20 Gbps in real-time, all within the optical domain without excess delays.(c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
Downloads
-
8468.pdf
- full text (Published version)
- |
- open access
- |
- |
- 4.80 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01HM6F6GG2EJ7383TVJW09YE6E
- MLA
- Ma, Chonghuai, et al. “Integrated Photonic Reservoir Computing with an All-Optical Readout.” OPTICS EXPRESS, vol. 31, no. 21, 2023, pp. 34843–54, doi:10.1364/OE.502354.
- APA
- Ma, C., Van Kerrebrouck, J., Deng, H., Sackesyn, S., Gooskens, E., Bai, B., … Bienstman, P. (2023). Integrated photonic reservoir computing with an all-optical readout. OPTICS EXPRESS, 31(21), 34843–34854. https://doi.org/10.1364/OE.502354
- Chicago author-date
- Ma, Chonghuai, Joris Van Kerrebrouck, Hong Deng, Stijn Sackesyn, Emmanuel Gooskens, Bing Bai, Joni Dambre, and Peter Bienstman. 2023. “Integrated Photonic Reservoir Computing with an All-Optical Readout.” OPTICS EXPRESS 31 (21): 34843–54. https://doi.org/10.1364/OE.502354.
- Chicago author-date (all authors)
- Ma, Chonghuai, Joris Van Kerrebrouck, Hong Deng, Stijn Sackesyn, Emmanuel Gooskens, Bing Bai, Joni Dambre, and Peter Bienstman. 2023. “Integrated Photonic Reservoir Computing with an All-Optical Readout.” OPTICS EXPRESS 31 (21): 34843–34854. doi:10.1364/OE.502354.
- Vancouver
- 1.Ma C, Van Kerrebrouck J, Deng H, Sackesyn S, Gooskens E, Bai B, et al. Integrated photonic reservoir computing with an all-optical readout. OPTICS EXPRESS. 2023;31(21):34843–54.
- IEEE
- [1]C. Ma et al., “Integrated photonic reservoir computing with an all-optical readout,” OPTICS EXPRESS, vol. 31, no. 21, pp. 34843–34854, 2023.
@article{01HM6F6GG2EJ7383TVJW09YE6E,
abstract = {{Integrated photonic reservoir computing has been demonstrated to be able to tackle different problems because of its neural network nature. A key advantage of photonic reservoir computing over other neuromorphic paradigms is its straightforward readout system, which facilitates both rapid training and robust, fabrication variation-insensitive photonic integrated hardware implementation for real-time processing. We present our recent development of a fully-optical, coherent photonic reservoir chip integrated with an optical readout system, capitalizing on these benefits. Alongside the integrated system, we also demonstrate a weight update strategy that is suitable for the integrated optical readout hardware. Using this online training scheme, we successfully solved 3-bit header recognition and delayed XOR tasks at 20 Gbps in real-time, all within the optical domain without excess delays.(c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement}},
author = {{Ma, Chonghuai and Van Kerrebrouck, Joris and Deng, Hong and Sackesyn, Stijn and Gooskens, Emmanuel and Bai, Bing and Dambre, Joni and Bienstman, Peter}},
issn = {{1094-4087}},
journal = {{OPTICS EXPRESS}},
language = {{eng}},
number = {{21}},
pages = {{34843--34854}},
title = {{Integrated photonic reservoir computing with an all-optical readout}},
url = {{http://doi.org/10.1364/OE.502354}},
volume = {{31}},
year = {{2023}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: