A neural network (NN)-assisted probabilistic shaping (PS) distribution matcher is proposed, in which the model is simplified by a structured optimization method. The NN algorithm can encode the information sequence, making the signal obey the Gaussian distribution, and can directly restore the received signal. In addition, the algorithm uses the novel training method at both ends of the transmitter and receiver so that the system performance is significantly improved. PS system verification experiments have been carried out under 16QAM-DMT modulation format. Under the hard decision forward error correction (FEC) threshold of 3.8*10⁻³ BER, the proposed system achieves 1.1 dB improvement compared to the traditional 16QAM-DMT system.

中文翻译：

---

数据中心光网络中神经网络分布匹配器辅助的概率整形通信系统

提出了一种神经网络（NN）辅助的概率整形（PS）分布匹配器，其中通过结构化优化方法简化了模型。NN算法可以对信息序列进行编码，使信号服从高斯分布，可以直接还原接收到的信号。此外，该算法在发送端和接收端采用了新颖的训练方法，显着提高了系统性能。PS系统验证实验已经在16QAM-DMT调制格式下进行。在 3.8*10 ^-3 BER的硬判决前向纠错 (FEC) 阈值下，与传统的 16QAM-DMT 系统相比，所提出的系统实现了 1.1 dB 的改进。