1. Mean Square Error (Mean Square Error / Quadratic Loss):
To ensure that the predicted MSE value is not particularly unusual, since the square of this error amplifying section.
2. The average absolute error (Mean Absolute Error):
MAE guaranteed performance predicted value in most cases good (not deliberately pipe outliers), because all errors are weighted according to the same linear scale.
3.Huber Loss:
Huber Loss between MSE and MAE, given outlier some extra weight but do not give too much.