Quantization of Recurrent Neural Network for Low-Complexity High-Speed IM/DD System Equalization Based on Neuron Clustering
Neural networks (NNs) are widely employed as effective equalizers in intensity-modulated direct-detection (IM/DD) links due to their excellent ability in dealing with nonlinear channel impairments. However, the complexity concern impedes the real-time application of NN-based receivers. To address th...
Saved in:
Published in | 2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings (ACP/POEM) pp. 1 - 4 |
---|---|
Main Authors | , , , , , , , , , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
04.11.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Neural networks (NNs) are widely employed as effective equalizers in intensity-modulated direct-detection (IM/DD) links due to their excellent ability in dealing with nonlinear channel impairments. However, the complexity concern impedes the real-time application of NN-based receivers. To address this issue, we propose mixed-precision quantization of recurrent NN (RNN)-based equalizers in a 100-Gb/s 15-km C-band IM/DD system, which saves about 73.3% and 22.4% memory compared with traditional floating-point-based and fixed-precision quantized RNN. A simple and effective neuron clustering approach is proposed to realize mixed-precision quantization of RNN without degrading system performance. |
---|---|
DOI: | 10.1109/ACP/POEM59049.2023.10369904 |