Question

If we are provided with an infinite sized training set which of the following classifier will have the lowest error probability?

A.  Decision tree

 

B.  K- nearest neighbor classifier

 

C.  Bayes classifier

 

D.  Support vector machine

​

Answer 1

it's C. Bayes classifier

Answer 2

If we are provided with an infinite sized training set, then the Bayes classifier will have the lowest error probability.

• Bayes error rate in statistical classification is the lowest possible error rate for any random outcome classifier.
• It is one of the simplest classifiers in which one of two categories are equivalent to the irreducible error.
• Since, it is the most probable classifier, it also maximizes the measure of performance.