Intelligent Machines: Perception, Learning, and Uncertainty

This course is an introduction to artificial intelligence, focusing on problems of perception, machine learning, and reasoning under uncertainty; supervised learning algorithms; decision trees; ensemble learning and boosting; neural networks, multilayer perceptrons and applications; support vector machines and kernal methods; clustering and unsupervised learning; probabilistic methods, parametric and non-parametric density estimation; maximum likelihood and maximum a posteriori estimates; Bayesian networks and graphical models; representation, inference, and learning; hidden Markov models; Markov decision processes and reinforcement learning; and computation learning theory. The recorded lectures are from the Harvard School of Engineering and Applied Sciences course Computer Science 181. Prerequisites: CSCI E-207, CSCI E-250, and STAT E-150, or the equivalent. (4 credits)