Machine Learning

CS 550 is a graduate survey of how machines learn from data, framing classification, clustering, and reinforcement learning as instances of the same underlying problem: inferring structure from examples under uncertainty. You'll move from Bayesian decision theory through decision trees, neural networks, and modern deep learning, with homeworks, a research essay, and a project where you implement algorithms, run experiments, and read recent literature. It assumes comfort with probability, linear algebra, and algorithms, and serves as the foundation for more specialized work in deep learning, NLP, computer vision, and data mining.