Abstract

We use active learning to reduce the number of probes needed for machinelearning-based QoT estimation. When building an estimation model based on Gaussian processes, only QoT instances that minimize estimation uncertainty are iteratively requested.

© 2019 The Author(s)

PDF Article
More Like This
Machine Learning for QoT Estimation of Unseen Optical Network States

Tania Panayiotou, Giannis Savva, Behnam Shariati, Ioannis Tomkos, and Georgios Ellinas
Tu2E.2 Optical Fiber Communication Conference (OFC) 2019

The Perks of Using Machine Learning for QoT Estimation with Uncertain Network Parameters

Matteo Lonardi, Jelena Pesic, Thierry Zami, and Nicola Rossi
NeM3B.2 Photonic Networks and Devices (Networks) 2020

Active vs Transfer Learning Approaches for QoT Estimation with Small Training Datasets

Dario Azzimonti, Cristina Rottondi, Alessandro Giusti, Massimo Tornatore, and Andrea Bianco
M4E.1 Optical Fiber Communication Conference (OFC) 2020

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription