4.20. Decision Trees
In this section we briefly review a large class of nonlinear classifiers known as decision trees. These are multistage decision systems in which classes are sequentially rejected until we reach a finally accepted class. To this end, the feature space is split into unique regions, corresponding to the classes, in a sequential manner. Upon the arrival of a feature vector, the searching of the region to which the feature vector will be assigned is achieved via a sequence of decisions along a path of nodes of an appropriately constructed tree. Such schemes offer advantages when a large number of classes are involved. The most popular decision trees are those that split the space into hyperrectangles with sides parallel to the ...
Get Pattern Recognition, 4th Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
