Study of Training Patterns for Employing Deep Neural Networks in Optical Communication Systems

Chun Yen Chuang, Li Chun Liu, Chia Chien Wei*, Jun Jie Liu, Lindor Henrickson, Chih Lin Wang, Young Kai Chen, Jye-Hong Chen

*此作品的通信作者

研究成果: Conference contribution同行評審

18 引文 斯高帕斯(Scopus)

摘要

Our investigation demonstrates that training patterns generated by Mersenne Twister pseudo-random number generator have potential to overcome the pattern effect. The resulting trained networks are capable of compensating the actual optical communication system response rather than merely predicting training signals.

原文English
主出版物標題2018 European Conference on Optical Communication, ECOC 2018
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781538648629
DOIs
出版狀態Published - 14 11月 2018
事件2018 European Conference on Optical Communication, ECOC 2018 - Rome, Italy
持續時間: 23 9月 201827 9月 2018

出版系列

名字European Conference on Optical Communication, ECOC
2018-September

Conference

Conference2018 European Conference on Optical Communication, ECOC 2018
國家/地區Italy
城市Rome
期間23/09/1827/09/18

指紋

深入研究「Study of Training Patterns for Employing Deep Neural Networks in Optical Communication Systems」主題。共同形成了獨特的指紋。

引用此