Machine Learning - Deep Learning Overview

1. Machine Learning

1. Decision tree

Decision tree decision tree is one of the main techniques used for classification and prediction. Decision tree learning is an instance-based inductive learning algorithm, which focuses on inferring from a set of unordered and irregular examples that are represented by decision trees. Classification rules. The purpose of constructing a decision tree is to find out the relationship between attributes and categories, and use it to predict the category of records of unknown category in the future. It adopts a top-down recursive way, compares the attributes in the internal nodes of the decision tree, judges the downward branch from the node according to different attribute values, and obtains the conclusion at the leaf node of the decision tree. The classification accuracy is high and the operation is simple. Its biggest advantage is that in the learning process, users do not need to know a lot of background knowledge, as long as the training sample set can be expressed in the form of attribute values, the decision tree learning algorithm can be used for classification. The main decision tree algorithms are ID3, C4.5 (C5.0), CART, PUBLIC, SLIQ and SPRINT algorithms. They have their own differences in the techniques used to select test attributes, the structure of the generated decision tree, the method and time of pruning, and whether they can handle large data sets. Decision trees are mainly used for classification and can also be used for regression. Use a broad classifier. Advantages: 1) The decision tree model is readable and has

share to: