本文共 1290 字，大约阅读时间需要 4 分钟。

?????????????

1. ????????????

????????????????????????????????????????????????????????????????????????????????

???????????[ P(y | x_1, x_2, \dots, x_n) = \frac{P(y) P(x_1, x_2, \dots, x_n | y)}{P(x_1, x_2, \dots, x_n)} ]

???

• ( y ) ?????
• ( x_1, x_2, \dots, x_n ) ?????

2. ?????????

????????????????????????????[ \hat{y} = \arg\max_y P(y) \prod_{i=1}^n P(x_i | y) ]

???????????????????????????????????????

3. ???????

????????????????????[ P(x_i | y) = \frac{1}{\sqrt{2\pi \sigma_y^2}} \exp\left(-\frac{(x_i - \mu_y)^2}{2\sigma_y^2}\right) ]

???

• ( \mu_y ) ??? ( y ) ???
• ( \sigma_y^2 ) ??? ( y ) ???

?????????? ( \mu_y ) ? ( \sigma_y^2 )?

4. ????????

?????????Multinomial Naive Bayes???????????????????????????[ P(x_i | y) = \theta_{yi} ]?? ( \theta_{yi} ) ??? ( y ) ?? ( i ) ???????

???????????[ \hat{\theta}{yi} = \frac{N{yi} + \alpha}{N_y + \alpha n} ]???

• ( N_{yi} ) ??? ( y ) ??? ( i ) ????
• ( N_y ) ??? ( y ) ?????
• ( \alpha ) ?????

5. ???????

????????Complement Naive Bayes?????????????????????????????????????????

6. Bernoulli?????

Bernoulli??????????????????0?1???????[ P(x_i | y) = \theta_{yi} ]

???????????[ \hat{\theta}{yi} = \frac{1}{N_y} \sum{x \in T} x_i ]

7. ?-of-core Naive Bayes????

?-of-core Naive Bayes??????????????????????????????????????

????

转载地址：http://ijwr.baihongyu.com/