November 2017
Beginner
286 pages
8h 13m
English
Which way (which approach) a data scientist will go or take to improve a model's performance and convert it from a weak learner into a strong learner will ultimately depend on many factors, but in the end, the approach taken depends on the individual problem.
AdaBoost (also known as Adaptive Boosting) is an iterative algorithm using a designated number of iterations or rounds to improve on a weak learner. This algorithm starts by training/testing a weak learner on data, weighting each example equally. The examples which are misclassified get their weights increased for the next round(s), while those that are correctly classified get their weights decreased.
We will know about AdaBoost later in this chapter.
Read now
Unlock full access