（菜鸟求助）关于《The Elements of Statistical Learning》第二章某句话求助 orz

wuhuang89

本人完全是小白额，这学期选了数据挖掘的课，正在看《The Elements of Statistical Learning》，线代的基础不好，很多不明白，向各位大大求助：

2.3.3章 “From Least Squares to Nearest Neighbors”

“First we generated 10 means mk from a bivariate Gaussian distribution N((1, 0)T , I) and labeled this class BLUE. Similarly, 10 more were drawn from N((0, 1)T , I) and labeled class ORANGE. Then for each class we generated 100 observations as follows: for each observation,we picked an mk at random with probability 1/10, and then generated a N(mk, I/5), thus leading to a mixture of Gaussian clusters for each class.”

这里面generate的新分布N(mk, I/5)中， I/5是怎么得来的呢？想了半天想不出来T-T

高歌人未老

我个人的理解是这个covariance matrix 选择的关键在于要比之前生成mean用的那个covariance matrix（单位阵I）小（比如说在positive definite意义下（I-I/5)仍然是正定的)，不然classification的效果可能会不好（想象一下不用I/5,用nI当n趋于无穷时候的情况）。至于去1/5应该是相对随意的。