Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Sparsely-Connected Cascade Recurrent Neural Network-Based Nonlinear Equalizer for a 100-Gb/s PAM4 Optical Interconnect

Not Accessible

Your library or personal account may give you access

Abstract

A sparsely-connected cascade recurrent neural network is proposed based on pruning which enables a 100-Gb/s 15-km PAM4 transmission using a bandwidth-limited DML. Compared with the fully-connected counterpart, 21.66% connections are saved without degrading system performance.

© 2021 The Author(s)

PDF Article
More Like This
Cascade Recurrent Neural Network Enabled 100-Gb/s PAM4 Short-Reach Optical Link Based on DML

Zhaopeng Xu, Chuanbowen Sun, Tonghui Ji, Honglin Ji, and William Shieh
W2A.45 Optical Fiber Communication Conference (OFC) 2020

Computationally-Efficient Sparsely-Connected Multi-Output Neural Networks for IM/DD System Equalization

Zhaopeng Xu, Shuangyu Dong, Honglin Ji, Jonathan H. Manton, and William Shieh
W2A.26 Optical Fiber Communication Conference (OFC) 2022

Investigation on the Impact of Additional Connections to Feedforward Neural Networks for Equalization in PAM4 Short-Reach Direct Detection Links

Zhaopeng Xu, Chuanbowen Sun, Tonghui Ji, Shuangyu Dong, Xian Zhou, and William Shieh
S4I.1 Asia Communications and Photonics Conference (ACP) 2020

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All Rights Reserved