This course explores a selected area relevant to statistical machine learning in depth, and will be taught by an SML staff member of internationally recognised standing and research interest in that area. Based on current SML staffing, this will be one of:kernel methodsstructured probabilistic modelsreinforcement learningconvex analysis and optimisationtopics in information theorydecision theorydeep learning differentiable optimisation in deep learningOver the past several years the content has alternated between “convex analysis and optimisation” and “differentiable optimisation in deep learning". Students should contact the course convenor to find out what topic is planned for the coming semester.
Additional source review: awaiting review. Published wording is shown below.
Some conditions may need additional evidence or clarification. These are prototype interpretations, not ANU decisions or degree-completion checks.
Requisite and Incompatibility
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.
Referenced entries (2)
Links and code mentions retain their original context above. They may describe options, prerequisites or exclusions.
Learning Outcomes
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)
Published offerings
Future offerings are indicative. Only recognised 2027 sessions with a published class number are offered in the enrolment demo.
| Year | Session | Class number | Class start date | Last day to enrol | Census date | Class end date | Mode Of Delivery | Class Summary |
|---|---|---|---|---|---|---|---|---|
| 2027 | First Semester | 5051 | 22 Feb 2027 | 01 Mar 2027 | 31 Mar 2027 | 28 May 2027 | In Person | N/A |
| 2028 | First Semester | 6460 | 21 Feb 2028 | 28 Feb 2028 | 31 Mar 2028 | 26 May 2028 | In Person | N/A |
Complete offering text
ANU utilises MyTimetable to enable students to view the timetable for their enrolled courses, browse, then self-allocate to small teaching activities / tutorials so they can better plan their time. Find out more on the Timetable webpage. The list of offerings for future years is indicative only. Class summaries, if available, can be accessed by clicking on the View link for the relevant class number. 2027 2028 First Semester Class number Class start date Last day to enrol Census date Class end date Mode Of Delivery Class Summary 5051 22 Feb 2027 01 Mar 2027 31 Mar 2027 28 May 2027 In Person N/A First Semester Class number Class start date Last day to enrol Census date Class end date Mode Of Delivery Class Summary 6460 21 Feb 2028 28 Feb 2028 31 Mar 2028 26 May 2028 In Person N/A
Source evidence (1 saved copy)
Matching copies share this record. Their original file locations and checksums are retained.
assets/Courses/Data Science/8000/Advanced Topics in Machine Learning/Advanced Topics in Machine Learning - ANU.html
Published ANU page · saved page URL
SHA-256: 45456f49f1647b570fee82d716ead4dab17f6af67ce7c44d1ab7adee901b2537