Abstract

A hybrid machine learning (HML) model combining a-priori and a-posteriori knowledge is implemented and tested, which is shown to reduce the prediction error and training complexity, compared to an analytical or neural network learning model.

© 2020 The Author(s)

PDF Article
More Like This
Toward Deployment of ML in Optical Networks, Transfer Learning, Monitoring and Modelling

Paurakh Paudyal, Shuangyi Yan, and Dimitra Simeonidou
S4C.2 Asia Communications and Photonics Conference (ACPC) 2020

Hybrid Learning Assisted Abstraction for Service Performance Assessment Over Multi-Domain Optical Networks

Rui Wang, Xi Chen, Zhengguang Gao, Shuangyi Yan, Reza Nejabati, and Dimitra Simeonidou
M1B.2 Optical Fiber Communication Conference (OFC) 2020

Performance Prediction of Established Lightpaths Using Machine Learning and Field Data

Christine Tremblay
C1F_2 Conference on Lasers and Electro-Optics/Pacific Rim (CLEOPR) 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 OSA member, or as an authorized user of your institution.

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