Home > Poster


Generalization Properties of Machine Learning-Based Raman Models (Th1A.28)

Presenter: Uiara de Moura, Danmarks Tekniske Universitet

We investigate the generalization capabilities of neural network-based Raman amplifier models. The new proposed model architecture, including fiber parameters as inputs, can predict Raman gains of fiber types unseen during training, unlike previous fiber-specific models.

Authors:Uiara de Moura, Danmarks Tekniske Universitet / Darko Zibar, Danmarks Tekniske Universitet / Margareth Rosa Brusin, Polito / Andrea Carena, Polito / Francesco Da Ros, Danmarks Tekniske Universitet

Poster Presentation

Authentication Required

Access to poster content is available to logged in registered attendees, please login now to participate.