Image classification with a 3-Layer SOA-based photonic integrated neural network

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

1 Citaat (Scopus)

Samenvatting

We demonstrate for the first time Iris flowers classification by implementing a trained 3-layer neural network with an SOA-based InP cross-connect chip. Classification accuracy of 85.8% is achieved, 9.2% lower than what obtained via a computer.

Originele taal-2Engels
TitelOECC/PSC 2019 - 24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing 2019
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
Aantal pagina's3
ISBN van elektronische versie978-4-88552-321-2
DOI's
StatusGepubliceerd - 1 jul 2019
Evenement24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing, OECC/PSC 2019 - Fukuoka, Japan
Duur: 7 jul 201911 jul 2019

Congres

Congres24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing, OECC/PSC 2019
LandJapan
StadFukuoka
Periode7/07/1911/07/19

Vingerafdruk Duik in de onderzoeksthema's van 'Image classification with a 3-Layer SOA-based photonic integrated neural network'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Shi, B., Calabretta, N., & Stabile, R. (2019). Image classification with a 3-Layer SOA-based photonic integrated neural network. In OECC/PSC 2019 - 24th OptoElectronics and Communications Conference/International Conference Photonics in Switching and Computing 2019 [8817694] Institute of Electrical and Electronics Engineers. https://doi.org/10.23919/PS.2019.8817694