Advanced Topics in Machine Learning

To enrol in this course you must have completed COMP6670 Introduction to Machine Learning or COMP8600 Statistical Machine Learning. Additional Prerequisite courses for the Advanced Topic will be listed on the SoCo website (Special Topics in Computing page ) when the course topic is announced. Students who meet the pre-requisites can request a permission code following the instructions for Enrolling in CECC courses.

Upon successful completion, students will have the knowledge and skills to:

Distinguish definitions of key concepts in convex analysis, including convexity of sets and functions, subgradients, and the convex dual

Produce a formal optimization problem from a high-level description and determine whether the problem is convex

Recognize standard convex optimization problems such as linear programs and quadratic programs

Derive results about convex functions such as Jensen’s inequality

Derive the standard (dual) quadratic program for support vector machines and understand the extension to max-margin methods for structured prediction

Implement and analyse gradient descent algorithms such as stochastic gradient descent and mirror descent

Understanding advanced concepts in deep learning and relate them to principles from convex optimisation

Implement a simple algorithms and differentiable models using a common deep learning framework (such as PyTorch)

Dr Mara Quinn is the fictional reviewer assigned to COMP8650 in this prototype. The selected course determines where a request goes.