For the first time, multi-task learning is proposed to improve the flexibility of NN-based equalizers in coherent systems. A "single" NN-based equalizer improves Q-factor by up to 4 dB compared to CDC, without re-training, even with variations in launch power, symbol rate, or transmission distance.

翻译：首次提出采用多任务学习提高相干系统中基于神经网络（NN）均衡器的灵活性。与色散补偿器（CDC）相比，一个“单一”的NN均衡器在发射功率、符号速率或传输距离变化的情况下，无需重新训练即可将Q因子提升高达4 dB。