Dataset used in training our artificial neural network model

Here we present the input-output dataset used in training our artificial neural network model to predict the performance of an InP Mach-Zehnder modulator with arbitary key design parameter values. The data have been normalized to zero-mean and unit variance to ensure equal weight of each input and output parameters in deep learning process.

本研究提供了用于训练人工神经网络模型的输入输出数据集，该模型可基于任意给定的关键设计参数值，预测磷化铟马赫-曾德尔调制器（InP Mach-Zehnder modulator）的性能。为确保深度学习过程中各输入与输出参数拥有同等权重，本数据集已被归一化为零均值与单位方差。