Machine learning makes it possible to construct a mathematical model from data, including a large number of variables that are not known in advance. The parameters are configured as you go through a learning phase, which uses training data sets to find links and classifies them. The different machine learning methods are chosen by the designers according to the nature of the tasks to be performed (grouping, decision tree). These methods are usually classified into 3 categories: human-supervised learning, unsupervised learning, and unsupervised learning by reinforcement. These 3 categories group together different methods including neural networks, deep learning etc.