Improving Time Series Recognition and Prediction with Networks and Ensembles of Passive Photonic Reservoirs

Simple item page
dc.contributor.authorFreiberger, Matthias
dc.contributor.authorSackesyn, Stijn
dc.contributor.authorMa, Chonghuai
dc.contributor.authorKatumba, Andrew
dc.contributor.authorBienstman, Peter
dc.contributor.authorDambre, Joni
dc.date.accessioned2022-11-29T20:06:07Z
dc.date.available2022-11-29T20:06:07Z
dc.date.issued2019
dc.description.abstractAs 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 work 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.en_US
dc.identifier.citationFreiberger, M., Sackesyn, S., Ma, C., Katumba, A., Bienstman, P., & Dambre, J. (2019). Improving time series recognition and prediction with networks and ensembles of passive photonic reservoirs. IEEE Journal of Selected Topics in Quantum Electronics, 26(1), 1-11.en_US
dc.identifier.urihttps://ieeexplore.ieee.org/abstract/document/8772153/
dc.identifier.urihttps://nru.uncst.go.ug/handle/123456789/5537
dc.language.isoenen_US
dc.publisherIEEE Journal of Selected Topics in Quantum Electronicsen_US
dc.subjectintegrated photonic reservoir computingen_US
dc.subjectdeep reservoir computingen_US
dc.subjectScalable reservoir computingen_US
dc.subjectUnconventional computingen_US
dc.subjectNeuro-inspired computingen_US
dc.subjectNeuromorphic computing.en_US
dc.titleImproving Time Series Recognition and Prediction with Networks and Ensembles of Passive Photonic Reservoirsen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Improving Time Series Recognition and Prediction.pdf
Size:
440.77 KB
Format:
Adobe Portable Document Format
Description:
Article
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Engineering and Technology