INFO 7001 Advanced Machine Learning

Credit Points 10

Legacy Code 301119

Coordinator Oliver Obst Opens in new window

Description Advanced Machine Learning explores modern methods of classification, clustering and regression to make predictions and analyse different forms of data. Issues that face all machine learning methods, such as model evaluation, assessment and generalisation will also be analysed.

School Computer, Data & Math Sciences

Student Contribution Band HECS Band 1 10cp

Check your HECS Band contribution amount via the Fees page.

Level Postgraduate Coursework Level 7 subject

Pre-requisite(s) MATH 7012

Restrictions Students must be enrolled in a postgraduate program.

Assumed Knowledge

Fundamentals of computer programming and basic linear algebra.

Learning Outcomes

On successful completion of this subject, students should be able to:
  1. Describe appropriate machine learning methods for given problems.
  2. Fit modern machine learning models to data.
  3. Make predictions based on a fitted machine learning model.
  4. Analyse data based on a fitted machine learning model.
  5. Evaluate the utility of a machine learning method for given data.

Subject Content

1. Introduction to Machine Learning
2. Support Vector Machines
3. Neural Networks
4. Reinforcement Learning
5. Manifold/Metric Learning


The following table summarises the standard assessment tasks for this subject. Please note this is a guide only. Assessment tasks are regularly updated, where there is a difference your Learning Guide takes precedence.

Item Length Percent Threshold Individual/Group Task
Online quizzes 5x60 minutes 20 N Individual
Project 15 pages 50 N Individual
Project presentation 15 mins 30 N Individual

Prescribed Texts

  • Sutton, R. S., Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). Cambridge, Massachusets: The MIT Press.

Teaching Periods

2022 Semester 2

Parramatta - Victoria Rd


Subject Contact Oliver Obst Opens in new window

Attendance Requirements 80% attendance rate is imposed in all core subjects’ due to the nature of class activities that are aligned with subject assessments.

View timetable Opens in new window