CMPUT 466/566 - Machine Learning

Overview

Learning is essential for many real-world tasks, including adaptive control, recognition, diagnosis, forecasting, and data-mining. This course covers foundational methods, particularly for supervised learning, introducing many classical regression and classification algorithms. More advanced modelling techniques will also be introduced, including kernels and neural networks. The course will also provide the formal foundations for understanding when learning is possible and practical.

Objectives

  • Understand how to formalize prediction problems
  • Understand the basics of deriving learning algorithms
  • Be able to determine when learning is likely to succeed, when it is cost-effective and when to use which algorithm
  • Understand the basics of evaluating algorithms and their theoretical properties

Course Work

  • Assignments
  • Projects
  • Final Exam