[WP4-B] Poster Session 2

[WP4-B10] Implementing Deep Neural Network for Signal Transmission Distortion Mitigation of PAM-4 Generated by Silicon Mach-Zehnder Modulator

Yung Hsu¹, Chun-Yen Chuang¹, Yeyu Tong², 〇Chi-Wai Chow¹, Jyehong Chen¹, Yin-Chieh Lai¹, Chien-Hung Yeh³, Young-Kai Chen⁴, Hon Ki Tsang² (¹National Chiao Tung Univ., Taiwan, ²Chinese Univ. of Hong Kong, Hong Kong, ³Feng Chia Univ., Taiwan, ⁴DARPA, U.S.A)

Keywords:Access Network and Subsystem, Data Center Network and Subsystem

We propose and demonstrate a distortion mitigation of 50-Gbit/s PAM-4 signal generated by a silicon-based Mach-Zehnder-modulator (SiMZM) after 20-km single-mode-fiber transmission via deep-neural-network (DNN). The implementation of a 2-layer DNN is discussed.