Paper

Paper

Changelog Terms Privacy Issues Docs Support Foundation About

Towards Low Computational Complexity for Neural Network-B... | ResearchHub

Paper

Paper

Supporters

Support the authors with ResearchCoin

Topics

Computer Science

Artificial Intelligence

Electrical And Electronic Engineering

Computer Networks And Communications

DOI

10.1364/ofc.2021.th1a.47

Changelog Terms Privacy Issues Docs Support Foundation About

Towards Low Computational Complexity for Neural Network-Based Equalization in PAM4 Short-Reach Direct Detection Systems by Multi-Symbol Prediction

0

Authors

Zhaopeng Xu

Zhaopeng Xu•Chuanbowen Sun•William Shieh

Published

January 1, 2021

Abstract

We propose NN-based multi-symbol equalization for a 50-Gb/s PAM4 direct-detection link which significantly reduces computational complexity without sacrificing BER performance of conventional single-output NNs. Complexity reduction of 42.7% is achieved when 8 outputs are selected.

Supporters

Support the authors with ResearchCoin

Topics

Computer Science

Artificial Intelligence

Electrical And Electronic Engineering

Computer Networks And Communications

DOI

10.1364/ofc.2021.th1a.47