Handbook home
Statistical Machine Learning (COMP90051)
Graduate courseworkPoints: 12.5Dual-Delivery (Parkville)
From 2023 most subjects will be taught on campus only with flexible options limited to a select number of postgraduate programs and individual subjects.
To learn more, visit COVID-19 course and subject delivery.
About this subject
- Overview
- Eligibility and requirements
- Assessment
- Dates and times
- Further information
- Timetable(opens in new window)
Contact information
Semester 1
Ben Rubinstein
Semester 2
Trevor Cohn
Overview
Availability | Semester 1 - Dual-Delivery Semester 2 - Dual-Delivery |
---|---|
Fees | Look up fees |
AIMS
With exponential increases in the amount of data becoming available in fields such as finance and biology, and on the web, there is an ever-greater need for methods to detect interesting patterns in that data, and classify novel data points based on curated data sets. Learning techniques provide the means to perform this analysis automatically, and in doing so to enhance understanding of general processes or to predict future events.
Topics covered will include: supervised learning, semi-supervised and active learning, unsupervised learning, kernel methods, probabilistic graphical models, classifier combination, neural networks.
This subject is intended to introduce graduate students to machine learning though a mixture of theoretical methods and hands-on practical experience in applying those methods to real-world problems.
INDICATIVE CONTENT
Topics covered will include: linear models, support vector machines, random forests, AdaBoost, stacking, query-by-committee, multiview learning, deep neural networks, un/directed probabilistic graphical models (Bayes nets and Markov random fields), hidden Markov models, principal components analysis, kernel methods.
Intended learning outcomes
On completion of this subject the student is expected to:
- Describe a range of machine learning algorithms
- Design, implement and evaluate learning systems to solve real-world problems, based on an appreciation of their relative suitability to different tasks
Generic skills
On completion of the subject students should have the following skills:
- Ability to undertake problem identification, formulation, and solution
- Ability to utilise a systems approach to complex problems and to design and operational performance ability to manage information and documentation
- Capacity for creativity and innovation
- Ability to communicate effectively both with the engineering team and the community at large
Last updated: 31 January 2024
Eligibility and requirements
Prerequisites
Students must meet one of the following prerequisite options:
Option 1
One of
Code | Name | Teaching period | Credit Points |
---|---|---|---|
COMP90049 | Introduction to Machine Learning |
Semester 2 (Dual-Delivery - Parkville)
Semester 1 (Dual-Delivery - Parkville)
|
12.5 |
COMP30027 | Machine Learning | Semester 1 (Dual-Delivery - Parkville) |
12.5 |
COMP30018 | Knowledge Technologies | No longer available |
Option 2
Admission into the MC-DATASC Master of Data Science
AND
One of
Code | Name | Teaching period | Credit Points |
---|---|---|---|
COMP20008 | Elements of Data Processing |
Semester 2 (Dual-Delivery - Parkville)
Semester 1 (Dual-Delivery - Parkville)
|
12.5 |
MAST90105 | Methods of Mathematical Statistics | Semester 1 (Dual-Delivery - Parkville) |
25 |
Option 3
Admission into or selection of one of the following:
- 100pt Program course entry point in the MC-IT Master of Information Technology
- 150pt Program course entry point in the MC-IT Master of Information Technology
- Distributed Computing specialisation (formal) in the MC-IT Master of Information Technology
- Computing specialisation (formal) in the MC-IT Master of Information Technology
- Artificial Intelligence specialisation (formal) in the MC-IT Master of Information Technology
Option 4
Admission into the 100pt Program course entry point in the MC-IT Master of Information Technology
AND
Selection of the Cyber Security specialisation (formal) in the MC-IT Master of Information Technology
Option 5
Admission into the MC-DATASC Master of Data Science
AND
Selection of the Data Science Background Stream
Corequisites
None
Non-allowed subjects
433-484 Machine Learning
433-679 Evolutionary and Neural Computation
433-680 Machine Learning
433-684 Machine Learning
Recommended background knowledge
Basic probability
Inherent requirements (core participation requirements)
The University of Melbourne is committed to providing students with reasonable adjustments to assessment and participation under the Disability Standards for Education (2005), and the Assessment and Results Policy (MPF1326). Students are expected to meet the core participation requirements for their course. These can be viewed under Entry and Participation Requirements for the course outlines in the Handbook.
Further details on how to seek academic adjustments can be found on the Student Equity and Disability Support website: http://services.unimelb.edu.au/student-equity/home
Last updated: 31 January 2024
Assessment
Description | Timing | Percentage |
---|---|---|
Two projects due around weeks 7 and 11.
| From Week 7 to Week 11 | 50% |
Fortnightly online quizzes, marked based on the best 5 results from 6 quizzes.
| Every second week | 10% |
One 2 hour end of semester examination.
| End of semester | 40% |
Additional details
Assessment for this subject addresses both Intended Learning Outcomes (ILOs)
Last updated: 31 January 2024
Dates & times
- Semester 1
Principal coordinator Ben Rubinstein Mode of delivery Dual-Delivery (Parkville) Contact hours 36 hours, comprising of two 1-hour lectures and one 1-hour tutorial per week Total time commitment 200 hours Teaching period 28 February 2022 to 29 May 2022 Last self-enrol date 11 March 2022 Census date 31 March 2022 Last date to withdraw without fail 6 May 2022 Assessment period ends 24 June 2022 Semester 1 contact information
Ben Rubinstein
- Semester 2
Principal coordinator Trevor Cohn Mode of delivery Dual-Delivery (Parkville) Contact hours 36 hours, comprising of two 1-hour lectures and one 1-hour tutorial per week Total time commitment 200 hours Teaching period 25 July 2022 to 23 October 2022 Last self-enrol date 5 August 2022 Census date 31 August 2022 Last date to withdraw without fail 23 September 2022 Assessment period ends 18 November 2022 Semester 2 contact information
Trevor Cohn
Time commitment details
200 hours
Last updated: 31 January 2024
Further information
- Texts
Prescribed texts
None
- Subject notes
LEARNING AND TEACHING METHODS
The subject is delivered through a combination of lectures and tutorials. One feature of the subject is that the projects are designed to be relatively open-ended and broad enough that students have scope to get hands-on experience implementing the breadth of material covered in the subject, as well as building off the subject content in innovating their own methods/researching related methods from the research literature and implementing them themselves.
INDICATIVE KEY LEARNING RESOURCES
Students will have access to lecture slides, readings relating to the lecture materials (both from a textbook and conference/journal papers), tutorial worksheets with worked solutions for all numeric problems, and sample reports to use in writing the project reports. Students are permitted to do their programming in any language and any programming environment/OS.
CAREERS / INDUSTRY LINKS
Machine learning has been growing rapidly in industry over the past two decades, with key industry players including Google, Microsoft, Amazon, Facebook and Twitter. There have been guest lecturers in the subject from organisations such as NICTA, which has a strong interest in machine learning (indeed one of the primary research groupings within NICTA is based on Machine Learning).
- Related Handbook entries
This subject contributes to the following:
Type Name Course Master of Data Science Course Master of Commerce (Decision, Risk and Financial Sciences) Course Ph.D.- Engineering Course Doctor of Philosophy - Engineering Course Master of Science (Computer Science) Course Master of Philosophy - Engineering Specialisation (formal) Computing Specialisation (formal) Distributed Computing - Available through the Community Access Program
About the Community Access Program (CAP)
This subject is available through the Community Access Program (also called Single Subject Studies) which allows you to enrol in single subjects offered by the University of Melbourne, without the commitment required to complete a whole degree.
Entry requirements including prerequisites may apply. Please refer to the CAP applications page for further information.
Additional information for this subject
Subject coordinator approval required.
- Available to Study Abroad and/or Study Exchange Students
This subject is available to students studying at the University from eligible overseas institutions on exchange and study abroad. Students are required to satisfy any listed requirements, such as pre- and co-requisites, for enrolment in the subject.
Last updated: 31 January 2024