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

Zhaopeng Xu,Shuangyu Dong,Honglin Ji,Jonathan H. Manton,William Shieh

2022 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXHIBITION (OFC)（2022）

引用 2|浏览3

暂无评分

摘要

Low-complexity sparsely-connected multi-output neural networks are proposed for equalization in a 50-Gb/s 25-km PAM4 IM/DD system. Compared with traditional fully-connected single-output counterparts, a gross complexity reduction of 60.4%/56.7% can be achieved with 2-layer FNN/C-FNN architecture. (C) 2022 The Author(s)

查看译文

关键词

computationally-efficient sparsely-connected multioutput neural networks,low-complexity sparsely-connected multioutput neural networks,PAM4 IM-DD system,fully-connected single-output counterparts,2-layer FNN-C-FNN architecture,feedforward neural network,intensity-modulated directly-detected systems

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要