|
|
Line 1: |
Line 1: |
| {{Underlinked|date=March 2013}}
| | When choosing an anchor kit, so this was made to anchor onto a structure and free-standing metal carports, whether electric or gas generated heat.<br><br>If you liked this post and you would such as to receive even more facts pertaining to carports in southern ohio, [http://andrieconstruction.com/metal-carports-in-southern-ohio/ mouse click the following website page], kindly visit our [http://web-Site.org/ web-site]. |
| | |
| In [[statistical classification]] the '''Bayes classifier''' minimises the [[probability]] of [[misclassification]].<ref name = "PTPR">{{cite book |author = Devroye, L., Gyorfi, L. & Lugosi, G. |year = 1996 |title = A probabilistic theory of pattern recognition| publisher=Springer | isbn=0-3879-4618-7}}</ref>
| |
| | |
| ==Definition==
| |
| | |
| Suppose a pair <math>(X,Y)</math> takes values in <math>\mathbb{R}^d \times \{1,2,\dots,K\}</math>, where <math>Y</math> is the class label of <math>X</math>. This means that the [[conditional distribution]] of ''X'', given that the label ''Y'' takes the value ''r'' is given by
| |
| | |
| :<math>X\mid Y=r \sim P_r</math> for <math>r=1,2,\dots,K</math>
| |
| | |
| where "<math>\sim</math>" means "is distributed as", and where <math>P_r</math> denotes a probability distribution.
| |
| | |
| A classifier is a rule that assigns to an observation ''X''=''x'' a guess or estimate of what the unobserved label ''Y''=''r'' actually was. In theoretical terms, a classifier is a measurable function <math>C: \mathbb{R}^d \to \{1,2,\dots,K\}</math>, with the interpretation that ''C'' classifies the point ''x'' to the class ''C''(''x''). The probability of misclassification, or risk, of a classifier ''C'' is defined as
| |
| :<math>\mathcal{R}(C) = \operatorname{P}\{C(X) \neq Y\}.</math>
| |
| | |
| The Bayes classifier is
| |
| :<math>C^\text{Bayes}(x) = \underset{r \in \{1,2,\dots, K\}}{\operatorname{argmax}} \operatorname{P}(Y=r \mid X=x).</math>
| |
| | |
| In practice, as in most of statistics, the difficulties and subtleties are associated with modeling the probability distributions effectively -- in this case, <math>\operatorname{P}(Y=r \mid X=x)</math>. The Bayes classifier is one of the useful benchmarks in [[statistical classification]].
| |
| | |
| The excess risk of a general classifier <math>C</math> (possibly depending on some training data) is defined as <math>\mathcal{R}(C) - \mathcal{R}(C^\text{Bayes}).</math>
| |
| Thus this non-negative quantity is important for assessing the performance of different classification techniques. A classifier is said to be [[Consistency (statistics)|consistent]] if the excess risk converges to zero as the size of the training data set tends to infinity.{{cn|date=March 2013}}
| |
| | |
| ==See also==
| |
| *[[Naive Bayes classifier]]
| |
| | |
| ==References==
| |
| {{reflist|1}}
| |
| | |
| [[Category:Bayesian statistics]]
| |
| [[Category:Statistical classification]]
| |
When choosing an anchor kit, so this was made to anchor onto a structure and free-standing metal carports, whether electric or gas generated heat.
If you liked this post and you would such as to receive even more facts pertaining to carports in southern ohio, mouse click the following website page, kindly visit our web-site.