1. Multiple Variables

2. Gradient Descent For Multiple Variables

3. Gradient Descent in Practice I - Feature Scaling

特征缩放和均值归一化
通过特征缩放和均值归一化可以将梯度下降的速度变得更快，让梯度下降收敛所需的循环更少。
Two techniques to help with this are feature scaling and mean normalization