AdaBoost算法原理及实例
Adaboost相关函数
-
弱分类器的误差率
e k = P ( G k ( x i ) ≠ y i ) = ∑ i = 1 m w k i I ( G k ( x i ) ≠ y i ) e_{k}=P\left(G_{k}\left(x_{i}\right) \neq y_{i}\right)=\sum_{i=1}^{m} w_{k i} I\left(G_{k}\left(x_{i}\right) \neq y_{i}\right) ek=P(Gk(xi)=yi)=i=1∑mwkiI(Gk(xi)=yi) -
弱分类器的 G k ( x ) G_k(x) Gk(x)的权重系数
a k = 1 2 l o g 1 − e k e k a_k = \frac{1}{2}log\frac{1-e_k}{e_k} ak=21logek1−ek -
弱分类器的权重系数
w k + 1 , i = w k , i Z K e x p ( − a k y i G k ( x i ) ) w_{k+1,i}=\frac{w_{k,i}}{Z_K}exp(-a_{k}y_{i}G_{k}(x_i)) wk+1,i=ZKwk,iexp(−akyiGk(x