MATH 748: Statistical Learning Theory and Applications

Bulletin Description

Prerequisites: Graduate standing; MATH 448; or permission of the instructor.

Study of the fundamental concepts of statistical and machine learning theory.

Student Learning Outcomes

Upon completion of this course a student should be able to

  • Understand the statistical principals and reasoning behind modern supervised & unsupervised learning methods.
  • Learn the whole process of creating data models, including data pre- processing, feature selection, model fitting, and model selection & evaluation.
  • Master the skills to perform data analysis using computer software, to interpret results and to communicate results effectively.
  • Obtain the hands-on experience by analyzing real data sets and make decent presentation about the results to audiences.

Course Outline

  • Statistical Decision Theory (1 week)
  • Support Vector Machines (2 weeks)
  • Discriminant Analysis (2 week)
  • Shrinkage Methods (2 weeks)
  • Ensemble Learning (2 weeks)
  • High-dimensional Classification (1 week)
  • Unsupervised Learning (3 weeks)
  • Feature Selection (1 week)

Textbooks & Software

  • An Introduction to Statistical Learning, with applications in R (2013), G. James, D. Witten, T. Hastie, R. Tibshirani.
  • The Elements of Statistical Learning, Data Mining, Inference and Prediction (2nd edition), Trevor Hastie, Robert Tibshirani, Jerome Friedman
  • Applied Predictive Modeling (2013), Max Kuhn, Kjell Johnson
  • R, by R Development Core Team