A Low-Complexity Recurrent Neural Network Based Joint Equalization and Decoding Method for Trellis Coded Modulation Link in Data Center
RNN-based joint equalization and decoding methods are proposed for data center with TCM signals. Numerical results show compared with traditional DSP algorithms, our method improves power sensitivity by 2.2dB@BER=3.8×10-3 with 96% reduced complexity.
Paper
Full text
A Low-Complexity Recurrent Neural Network Based Joint Equalization and Decoding Method for Trellis Coded Modulation Link in Data Center
Semantic Scholar · Engineering · 2020
Abstract
RNN-based joint equalization and decoding methods are proposed for data center with TCM signals. Numerical results show compared with traditional DSP algorithms, our method improves power sensitivity by 2.2dB@BER=3.8×10-3 with 96% reduced complexity.