We introduce neural network (NN)-based equalization in high-speed passive optical networks. Data feature engineering is proposed to improve performance of NN-based equalization. Besides, an unsupervised learning scheme for NN-based equalizer is proposed to train the model without known symbols of received signal.

© 2020 The Author(s)

PDF Article


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
Login to access OSA Member Subscription