本次分享几个容易混淆的量，分别为：
-
RMS:均方根值
-
RMSE: 均方根误差
-
Standard Deviation: 标准差
下面给出三个量的表达公式：
均方根值
Xrms=i=1NXiNN=X12+X22+...+XN2N"
role="presentation" style="box-sizing: border-box; outline: 0px;
display: inline; line-height: normal; word-spacing: normal;
word-wrap: normal; white-space: nowrap; float: none; direction:
ltr; max-width: none; max-height: none; min-width: 0px; min-height:
0px; border: 0px; padding: 0px; margin: 0px; word-break: break-all;
position: relative;">Xrms=∑Ni=1XNiN−−−−−−−−√=X21+X22+...+X2NN−−−−−−−−−−−−−−−−√Xrms=∑i=1NXiNN=X12+X22+...+XN2N
均方根误差
RMSE=i=1n(Xobs,iXmodel,i)2n"
role="presentation" style="box-sizing: border-box; outline: 0px;
display: inline; line-height: normal; word-spacing: normal;
word-wrap: normal; white-space: nowrap; float: none; direction:
ltr; max-width: none; max-height: none; min-width: 0px; min-height:
0px; border: 0px; padding: 0px; margin: 0px; word-break: break-all;
position: relative;">RMSE=∑ni=1(Xobs,i−Xmodel,i)2n−−−−−−−−−−−−−−−−−−−√RMSE=∑i=1n(Xobs,i−Xmodel,i)2n
公式理解： 它是观测值与真值偏差的平方和观测次数n" role="presentation" style="box-sizing:
border-box; outline: 0px; display: inline; line-height: normal;
text-align: left; word-spacing: normal; word-wrap: normal;
white-space: nowrap; float: none; direction: ltr; max-width: none;
max-height: none; min-width: 0px; min-height: 0px; border: 0px;
padding: 0px; margin: 0px; word-break: break-all; position:
relative;">nn比值的平方根，在实际测量中，观测次数n" role="presentation" style="box-sizing:
border-box; outline: 0px; display: inline; line-height: normal;
text-align: left; word-spacing: normal; word-wrap: normal;
white-space: nowrap; float: none; direction: ltr; max-width: none;
max-height: none; min-width: 0px; min-height: 0px; border: 0px;
padding: 0px; margin: 0px; word-break: break-all; position:
relative;">nn总是有限的，真值只能用最可信赖（最佳）值来代替.方根误差对一组测量中的特大或特小误差反映非常敏感，所以，均方根误差能够很好地反映出测量的精密度。均方根误差，当对某一量进行甚多次的测量时，取这一测量列真误差的均方根差(真误差平方的算术平均值再开方)，称为标准偏差，以" role="presentation"
style="box-sizing: border-box; outline: 0px; display: inline;
line-height: normal; text-align: left; word-spacing: normal;
word-wrap: normal; white-space: nowrap; float: none; direction:
ltr; max-width: none; max-height: none; min-width: 0px; min-height:
0px; border: 0px; padding: 0px; margin: 0px; word-break: break-all;
position: relative;">σσ表示。" role="presentation"
style="box-sizing: border-box; outline: 0px; display: inline;
line-height: normal; text-align: left; word-spacing: normal;
word-wrap: normal; white-space: nowrap; float: none; direction:
ltr; max-width: none; max-height: none; min-width: 0px; min-height:
0px; border: 0px; padding: 0px; margin: 0px; word-break: break-all;
position: relative;">σσ反映了测量数据偏离真实值的程度，" role="presentation"
style="box-sizing: border-box; outline: 0px; display: inline;
line-height: normal; text-align: left; word-spacing: normal;
word-wrap: normal; white-space: nowrap; float: none; direction:
ltr; max-width: none; max-height: none; min-width: 0px; min-height:
0px; border: 0px; padding: 0px; margin: 0px; word-break: break-all;
position: relative;">σσ越小，表示测量精度越高，因此可用" role="presentation"
style="box-sizing: border-box; outline: 0px; display: inline;
line-height: normal; text-align: left; word-spacing: normal;
word-wrap: normal; white-space: nowrap; float: none; direction:
ltr; max-width: none; max-height: none; min-width: 0px; min-height:
0px; border: 0px; padding: 0px; margin: 0px; word-break: break-all;
position: relative;">σσ作为评定这一测量过程精度的标准。
标准差：
SD=sumi=1N(XiX)2n"
role="presentation" style="box-sizing: border-box; outline: 0px;
display: inline; line-height: normal; word-spacing: normal;
word-wrap: normal; white-space: nowrap; float: none; direction:
ltr; max-width: none; max-height: none; min-width: 0px; min-height:
0px; border: 0px; padding: 0px; margin: 0px; word-break: break-all;
position: relative;">SD=sumNi=1(Xi−X¯¯¯¯)2n−−−−−−−−−−−−−−−√SD=sumi=1N(Xi−X¯)2n
理解： 标准差是方差的算术平方根，也称均方差（Mean" role="presentation" style="box-sizing:
border-box; outline: 0px; display: inline; line-height: normal;
text-align: left; word-spacing: normal; word-wrap: normal;
white-space: nowrap; float: none; direction: ltr; max-width: none;
max-height: none; min-width: 0px; min-height: 0px; border: 0px;
padding: 0px; margin: 0px; word-break: break-all; position:
relative;">MeanMean Square" role="presentation" style="box-sizing:
border-box; outline: 0px; display: inline; line-height: normal;
text-align: left; word-spacing: normal; word-wrap: normal;
white-space: nowrap; float: none; direction: ltr; max-width: none;
max-height: none; min-width: 0px; min-height: 0px; border: 0px;
padding: 0px; margin: 0px; word-break: break-all; position:
relative;">SquareSquare Error" role="presentation" style="box-sizing:
border-box; outline: 0px; display: inline; line-height: normal;
text-align: left; word-spacing: normal; word-wrap: normal;
white-space: nowrap; float: none; direction: ltr; max-width: none;
max-height: none; min-width: 0px; min-height: 0px; border: 0px;
padding: 0px; margin: 0px; word-break: break-all; position:
relative;">ErrorError），是各数据偏离平均数的距离的平均数，它是离均差平方和平均后的方根，用" role="presentation"
style="box-sizing: border-box; outline: 0px; display: inline;
line-height: normal; text-align: left; word-spacing: normal;
word-wrap: normal; white-space: nowrap; float: none; direction:
ltr; max-width: none; max-height: none; min-width: 0px; min-height:
0px; border: 0px; padding: 0px; margin: 0px; word-break: break-all;
position: relative;">σσ表示，标准差能反映一个数据集的离散程度。
在机器学习训练模型时，MSE" role="presentation"
style="box-sizing: border-box; outline: 0px; display: inline;
line-height: normal; text-align: left; word-spacing: normal;
word-wrap: normal; white-space: nowrap; float: none; direction:
ltr; max-width: none; max-height: none; min-width: 0px; min-height:
0px; border: 0px; padding: 0px; margin: 0px; word-break: break-all;
position: relative;">MSEMSE 是最常用的，用来刻画模型的误差。
加载中，请稍候......
加载中…
喜欢