This paper compares three training strategies for low-precision photonic neural networks. The efficacy of the schemes is tested through circuital simulations on the photonic electronic multiplyaccumulate neuron (PEMAN) architecture with three different datasets.
Device-Informed Training Strategy for Low-Precision Photonic Neural Networks
De Marinis, Lorenzo;Paolini, Emilio;Andriolli, Nicola;Contestabile, Giampiero;
2025-01-01
Abstract
This paper compares three training strategies for low-precision photonic neural networks. The efficacy of the schemes is tested through circuital simulations on the photonic electronic multiplyaccumulate neuron (PEMAN) architecture with three different datasets.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Device-Informed_Training_Strategy_for_Low-Precision_Photonic_Neural_Networks.pdf
solo utenti autorizzati
Tipologia:
Documento in Pre-print/Submitted manuscript
Licenza:
Copyright dell'editore
Dimensione
639.51 kB
Formato
Adobe PDF
|
639.51 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
