Statistical Learning
0.5 Credit

Hours per week:
  • Lecture/Discussion: 3
  • Lab: 1.5 (biweekly)

The course covers the most current techniques used in statistical learning and data analysis, and their background theoretical results. Two basic groups of methods are covered in this course: supervised learning (classification and regression) and unsupervised learning (clustering). The supervised learning methods include Recursive Partitioning Tree, Random Forest, Linear Discriminant and Quadratic Discriminant Analysis, Neural Network, Support Vector Machine, K-nearest neighbour, and Regression. The unsupervised learning methods include Hierarchical Clustering, K-means, and Model-based Clustering methods. Furthermore, the course also covers dimension reduction techniques such as LASSO and Ridge Regression, and model checking criteria. Some data visualization methods will be introduced in this course as well.

Additional Course Information