The Problem of Overfitting
Example 1: Linear Regression(Housing)
Example 2: Logistic Regression
（g：sigmoid function）
Addressing Overfitting: lots of features and very little training data,then,overfitting can be a problem
The Solution:
Option 1: Reduce number of features
(1)Manually select which features to keep
(2)Model selection algorithm(模型选择算法)
Option 2:Regularization
(1)Keep all features, but reduce magnitude/ values
(2)Works well when we have a lot features
Cost Function
Example： Housing
——Features: x1 ,x2, x3, x4, x5, ....(Such as: the number of rooms, age,size,length...)
——Parameters: theta 1, theta 2, theta 3, ....
Regularized Linear Regression
Way 1: Gradient descent
Cost Function:
Target:
Repeat:{
}
Way 2: Normal equation
Advantage:
1.take care of any non-invertibility issues
2. to avoid overfitting eveb if you have a lot of features in a relatively small training set
Regularized Logistic Regression
Repeat:
{
}
