Method for training an adaptive statistical classifier to balance unigram prior factors

摘要

A statistical classifier is trained in a manner to remove biasing due to unequal frequencies of unigram priors. The relative frequencies of all classes in a training set of sample patterns is determined. Training patterns are then selected from the set and skipped or repeated in dependence upon the relative frequency of the class to which they belong. In this manner, the presentation of samples is balanced across the classes.