本文主要以Individual Calibration with Randomized Forecasting这一篇文章来说明写文章的规范。
1 配置说明
通常标题为 Experiment Setup,这里需要你介绍你所用的数据集、模型、(具体到用了什么结构、优化算法,结构可以放在附录)度量指标、baseline
1.1 数据集
本文用的数据集是 UCI crime and communities dataset,具体训练细节放在附录。
We use the UCI crime and communities dataset (Dua & Graff, 2017) and we predict the crime rate based on features of the neighborhood (such as racial composition). For training details and network architecturesee Appendix B.3. 2
1.2 Recalibration(baseline)
本文的baseline是Kuleshov et al提出的Post training recalibration(在训练之后的校准