An artificial neural network (ANN) based maximum-likelihood (ML) symbol detection is proposed for nonlinearity compensation in PAM-4. Its optimized architecture realizes 0.7-dB better sensitivity and 20-times lower complexity than the conventional ANN-based ML sequence detection.

© 2018 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