SOA-based photonic integrated deep neural networks for image classification

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

4 Citaten (Scopus)
5 Downloads (Pure)

Samenvatting

We successfully demonstrate classification of three classes of Iris flowers by implementing a trained neural network on an SOA-based InP cross-connect chip. Classification accuracy of 91.6% is achieved after a fine optimization procedure.

Originele taal-2Engels
Titel2019 Conference on Lasers and Electro-Optics, CLEO 2019 - Proceedings
SubtitelScience and Innovations, CLEO_SI 2019
Plaats van productieWashington
UitgeverijOptical Society of America (OSA)
Aantal pagina's2
ISBN van elektronische versie978-1-943580-57-6
DOI's
StatusGepubliceerd - mei 2019
EvenementCLEO: Science and Innovations, CLEO_SI 2019 - San Jose, Verenigde Staten van Amerika
Duur: 5 mei 201910 mei 2019

Congres

CongresCLEO: Science and Innovations, CLEO_SI 2019
LandVerenigde Staten van Amerika
StadSan Jose
Periode5/05/1910/05/19

Vingerafdruk Duik in de onderzoeksthema's van 'SOA-based photonic integrated deep neural networks for image classification'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Shi, B., Calabretta, N., & Stabile, R. (2019). SOA-based photonic integrated deep neural networks for image classification. In 2019 Conference on Lasers and Electro-Optics, CLEO 2019 - Proceedings: Science and Innovations, CLEO_SI 2019 [8750138] Optical Society of America (OSA). https://doi.org/10.1364/CLEO_SI.2019.SF1N.5