BUILT-IN WOLFRAM LANGUAGE SYMBOL
is an option for Classify and related functions that specifies explicit prior probabilities to assume for output classes, independent of anything deduced from the training set.
- ClassPriors-><|class1->p1,class2->p2,…|> specifies that the prior probability to classify a particular input as being in class should be .
- By default, the class priors are computed from the class frequencies of the training set.
- In ClassPriors-><|class1->p1,class2->p2,…|>, unspecified class priors will be set to their rescaled default value to ensure normalization of the distribution.
Train a classifier on an unbalanced training set:
Obtain class probabilities for a new example:
Set a uniform prior distribution for the classes:
Set the prior distribution of classes inside the classifier:
Priors of unspecified classes are functions of the remaining probability mass:
Introduced in 2014