Great post to look into.
Decision trees occupy an important place in machine learning. They form the basis of Random Forests, which are used extensively in real world systems. A famous example of this is Microsoft Kinect where Random Forests are used to track your body parts. The reason this technique is so popular is because it provides high accuracy with relatively little effort. They are fast to train and they are not computationally expensive. They are not sensitive to outliers either, which helps them to be robust in a variety of cases. So how exactly are they constructed? How are the nodes in the trees generated so that they are optimal?
View original post 778 more words