Two new classes of processing elements based on a generalized Mach-Zehnder architecture are proposed for neural networks applications in integrated optics. Both new processing elements are demonstrated experimentally on a silicon photonic platform and analyzed theoretically boosting further the toolbox for photonic neural networks.
Integrated Silicon Photonics Processing Elements for Neural Networks and switching applications / Velha, Philippe. - (2020), pp. 1-2. (Intervento presentato al convegno 2020 IEEE Photonics Conference, IPC 2020 tenutosi a Vancouver, BC, Canada nel 28 September 2020 - 01 October 2020) [10.1109/IPC47351.2020.9252342].
Integrated Silicon Photonics Processing Elements for Neural Networks and switching applications
Velha, Philippe
Primo
2020-01-01
Abstract
Two new classes of processing elements based on a generalized Mach-Zehnder architecture are proposed for neural networks applications in integrated optics. Both new processing elements are demonstrated experimentally on a silicon photonic platform and analyzed theoretically boosting further the toolbox for photonic neural networks.| File | Dimensione | Formato | |
|---|---|---|---|
|
Integrated_Silicon_Photonics_Processing_Elements_for_Neural_Networks_and_switching_applications.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
456.37 kB
Formato
Adobe PDF
|
456.37 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
