At this point, we have covered all of the topics most pertinent to boosting, so let's now get back to the main event, statistical boosting.
We have already offered a description of what statistical boosting is and what it is used for (a learning algorithm intended to reduce bias and variance and convert weak learners into strong ones).
Key to this concept is the idea of how learners inherently behave, with a weak learner defined as one which is only slightly correlated with the true classification (it can label examples better than random guessing). In contrast, a strong learner is one that is well-correlated with the true classification.
