One-shot learning for modulation format identification in evolving optical networksVisa övriga samt affilieringar
2017 (Engelska)Ingår i: Optics InfoBase Conference Papers, OSA - The Optical Society , 2017Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]
We report on the first successful application of one-shot machine learning scheme that identifies new modulation formats based on a single constellation diagram without re-training. 100% accuracy is achieved when expanding from 2 to 5 supported modulation formats. © 2019 The Author(s).
Ort, förlag, år, upplaga, sidor
OSA - The Optical Society , 2017.
Nyckelord [en]
Nanophotonics, Optical signal processing, Photonics, Constellation diagrams, Modulation formats, New modulation formats, One-shot learning, Modulation
Nationell ämneskategori
Naturvetenskap
Identifikatorer
URN: urn:nbn:se:ri:diva-42503Scopus ID: 2-s2.0-85077217282ISBN: 9781557528209 (tryckt)OAI: oai:DiVA.org:ri-42503DiVA, id: diva2:1384756
Konferens
Integrated Photonics Research, Silicon and Nanophotonics, IPRSN 2019, 29 July 2019 through 1 August 2017
Anmärkning
Conference code: 141568; Export Date: 9 January 2020; Conference Paper; Funding details: VINNOVA, 2017-01559; Funding details: Vetenskapsrådet, VR, 2016-04510; Funding text 1: This work was supported by VINNOVA within the project Centre for Software-Defined Optical Networks (2017-01559), by VR project PHASE (2016-04510), and by COST Action 15127 RECODIS. References
2020-01-102020-01-102025-09-23Bibliografiskt granskad