The chapter focuses on supervised machine learning, where algorithms learn to project input data on dedicated desired values. Starting with a simplistic evolutionary algorithm, the abstract idea of learning and its mathematical and programmatic concepts are presented. This approach is then applied to the Least Mean Squares adaptive filter, which is a learning algorithm from the field of filter theory and allows for an intuitive explanation of the concept of learning rates and iterative change based on quality functionals. As one of the most important methods of supervised learning, we introduce neural networks and provide simple program examples for training such methods for both classification and regression problems. With the transition to recurrent networks, a learning methodology is discussed that is particularly advantageous for use on time series data. Finally, we demonstrate the construction of decision trees, which are often used as a complementary tool to neural networks in situations where a decision based on statistical considerations makes sense.