This chapter introduces a very useful machine learning technique, ensemble learning, which can turn multiple models into a more powerful model. We will first study the basics of ensemble learning, including its definition, basic questions, major categories of algorithms, history, and challenges to figure out how it works, why it works, and what to use to make it work better. Next, three major categories of ensemble learning algorithms, i.e., bagging, boosting, and stacking, will be explained. The basic ideas and representative algorithms of these three categories of ensemble learning will be discussed with strict mathematical formulations and pseudo-code for guiding their applications.