特征選擇 - Filter、Wrapper、Embedded

Filter methods:

• information gain
• chi-square test
• fisher score
• correlation coefficient
• variance threshold

Wrapper methods:

• recursive feature elimination
• sequential feature selection algorithms
• genetic algorithms

Embedded methods:

• L1 (LASSO) regularization
  
  • 增加懲罰項（正則項），用於控制過擬合
  • regularized_cost = cost + regularization_penalty
  • LASSO的方式： λ∑i|wi| $\lambda \underset{i}{\sum }|w_i|$
• decision tree