课程: Machine Learning and AI Foundations: Decision Trees with KNIME

今天就学习课程吧！

今天就开通帐号，24,600 门业界名师课程任您挑！

The math behind regression trees

The math behind regression trees - KNIME教程

课程: Machine Learning and AI Foundations: Decision Trees with KNIME

开始一个月试用 购买团队方案

The math behind regression trees

“

- [Instructor] Let's talk a little bit about the math behind regression trees. Now, if you recall, classification trees use the Gini coefficient and some other factors to grow and then eventually prune the tree. With regression trees, it's a little bit different and that's what I want to talk about. So when we start predicting something like this miles per gallon example, we have at the top a predicted value of 23.8 miles per gallon. So there's no normality assumption, but for the moment, let's just assume that miles per gallon is somewhat like a bell curve, as you can see indicated there. What you're trying to do, or rather what the algorithm is trying to do as it works its way down the tree, is find branches where that bell curve is going to get increasingly tall and skinny as it branches and splits and works its way down to the bottom of the tree where you would find your leaf nodes. Now, why is that the case?…

内容