Yue, Yuanli, Liu, Shouju, Zhang, Ruibo, Luan, Tianxiang, Zhang, Ailing, Wang, Chao (2023) Experimental Investigation of an Optical Reservoir Computer with MZI-based Optical Mask. In: 2023 International Topical Meeting on Microwave Photonics (MWP). 2023 International Topical Meeting on Microwave Photonics (MWP). . IEEE (doi:10.1109/mwp58203.2023.10416575) (KAR id:105005)
PDF
Author's Accepted Manuscript
Language: English |
|
Download this file (PDF/425kB) |
Preview |
Request a format suitable for use with assistive technology e.g. a screenreader | |
Official URL: https://doi.org/10.1109/mwp58203.2023.10416575 |
Abstract
In this paper, we have experimentally demonstrated a novel all-optical masking solution in photonic time stretch reservoir computing to eliminate the need of high-speed signal generator for digital masks. By leveraging the high chirp rate generated through an unbalanced Mach-Zehnder Interferometer (MZI) structure, we achieved a random optical mask in the spectral domain. Optical wavelengths, acting as virtual reservoir nodes, enable spectral mixing within the reservoir layer. Thanks to time-spectrum mapping in the photonic time stretch system, equivalent temporal masking is obtained. The develop system exhibits memory capacity through delayed optical feedback process. A full photonic reservoir computing system is implemented. Two experiments of waveform and digit-spoken signal classification have been carried out. Our experimental results show that MZI-based optical mask enables superior performance in photonic time stretch reservoir computing.
Item Type: | Conference or workshop item (Proceeding) |
---|---|
DOI/Identification number: | 10.1109/mwp58203.2023.10416575 |
Additional information: | © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. For the purpose of open access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission. |
Subjects: | T Technology > TA Engineering (General). Civil engineering (General) |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts |
Funders: |
Engineering and Physical Sciences Research Council (https://ror.org/0439y7842)
National Natural Science Foundation of China (https://ror.org/01h0zpd94) |
SWORD Depositor: | JISC Publications Router |
Depositing User: | JISC Publications Router |
Date Deposited: | 16 Feb 2024 15:52 UTC |
Last Modified: | 05 Nov 2024 13:10 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/105005 (The current URI for this page, for reference purposes) |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):