Introduces the principles and algorithms of machine learning. Topics include (1) traditional machine learning, such as regressions, decision trees and ensemble learning, artificial neural networks, Bayesian learning, support vector machines, instance-based learning, unsupervised learning; (2) deep learning: such as recurrent networks, convoluntional neural networks, deep belief networks, deep generative models. Students are expected to implement various machine learning models and conduct experiments on real workd datasets.