Prediction: Machine Learning and Statistics
MIT's Sloan School course brings together the two fields that both aim at predicting outcomes from data: machine learning and statistics. Lectures cover core methods including regression, classification, clustering, and model selection, comparing how each discipline approaches the same underlying problem of generalizing from data. The course materials, published through MIT OpenCourseWare, include lecture notes, problem sets, and exam materials covering topics such as decision trees, support vector machines, boosting, and statistical estimation theory. It is aimed at an advanced audience already familiar with basic probability and linear algebra, and situates machine learning's roots in artificial intelligence alongside statistics' growth through modern computing. There is no instructor interaction or certificate, just the self-paced published materials, free to access online under MIT's open license.