Underfitting: There are many errors between the predicted value of the training set and the true value of the training set, which is called underfitting.
Overfitting: The predicted value of the training set completely fits the real value of the training set, which is called overfitting.
Overfitting is the training set is very good, but the test set does not work
How to avoid overfitting:
Add regular items L1, L2 (with squares, reduce high-order coefficients).
Regular term L2 derivation: