Introduction to Machine Learning (COMP90049)
Graduate courseworkPoints: 12.5Online and Dual-Delivery (Parkville)
Please refer to the return to campus page for more information on these delivery modes and students who can enrol in each mode based on their location.
About this subject
Contact information
Semester 1
Lea Frermann
Semester 2
Email: rashidi.l@unimelb.edu.au
Overview
| Availability | Semester 1 - Online Semester 2 - Dual-Delivery |
|---|---|
| Fees | Look up fees |
AIMS
Machine Learning is the study of making accurate, computationally efficient, interpretable and robust inferences from data, often drawing on principles from statistics. This subject aims to introduce students to the intellectual foundations of machine learning, including the mathematical principles of learning from data, algorithms and data structures for machine learning, and practical skills of data analysis.
INDICATIVE CONTENT
Indicative content includes: cleaning and normalising data, supervised learning (classification, regression, linear & non-linear models), and unsupervised learning (clustering), and mathematical foundations for a career in machine learning.
Intended learning outcomes
On completion of this subject students are expected to be able to:
- ILO 1 - Understand elementary mathematical concepts used in machine learning
- ILO 2 - Derive machine learning models from first principles
- ILO 3 - Design, implement, and evaluate machine learning systems for real-world problems
- ILO 4 - Identify the correct machine learning model for a given real-world problem
Generic skills
- On completion of this subject, students should have the following generic skills:
- General skills include the ability to undertake problem identification, formulation, and developing solutions especially exploiting acquired data
- In addition this subject exposes students to use various data processing tools and make them learn integration of these tools to build more complex software systems
- As a result the student will develop skills to utilise a systems approach to complex problems
Last updated: 3 November 2022
Eligibility and requirements
Prerequisites
One of the following:
| Code | Name | Teaching period | Credit Points |
|---|---|---|---|
| COMP20003 | Algorithms and Data Structures | Semester 2 (Dual-Delivery - Parkville) |
12.5 |
| Code | Name | Teaching period | Credit Points |
|---|---|---|---|
| COMP90038 | Algorithms and Complexity |
Semester 2 (Dual-Delivery - Parkville)
Semester 1 (Online)
|
12.5 |
| Code | Name | Teaching period | Credit Points |
|---|---|---|---|
| COMP20007 | Design of Algorithms | Semester 1 (Dual-Delivery - Parkville) |
12.5 |
| Code | Name | Teaching period | Credit Points |
|---|---|---|---|
| ENGR30003 | Numerical Programming for Engineers | No longer available |
OR
Admission into one of the following courses:
MC-ENG Master of Engineering (200 program only)
MC-IT Master of Information Technology, 100 or 150 pt program in Distributed Computing, Computing, Cyber Security or Artificial Intelligence
MC-IT Master of Information Technology, 100 pt program in Human-Centre Interaction
MC-SCICMP Master of Science (Computer Science)
MC-CS Master of Computer Science
Corequisites
None
Non-allowed subjects
| Code | Name | Teaching period | Credit Points |
|---|---|---|---|
| COMP30018 | Knowledge Technologies | No longer available |
AND
| Code | Name | Teaching period | Credit Points |
|---|---|---|---|
| COMP30027 | Machine Learning | Semester 1 (Dual-Delivery - Parkville) |
12.5 |
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: 3 November 2022
Assessment
| Description | Timing | Percentage |
|---|---|---|
Two short programming assignments.
| From Week 2 to Week 8 | 30% |
A final, open-ended (in terms of methodology) research project
| From Week 11 to Week 12 | 30% |
End of semester exam. Online, closed-book, 2 hours.
| During the examination period | 40% |
Additional details
Intended Learning Outcomes (ILOs) 1 and 2 are addressed in the lectures and workshops; ILOs 3 and 4 are addressed in the assignments and project; ILOs 1--4 are addressed in the exam.
Last updated: 3 November 2022
Dates & times
- Semester 1 - Online
Principal coordinator Lea Frermann Mode of delivery Online Contact hours 36 hours, comprising of two 1-hour lectures and one 1-hour tutorial per week Total time commitment 200 hours Teaching period 1 March 2021 to 30 May 2021 Last self-enrol date 12 March 2021 Census date 31 March 2021 Last date to withdraw without fail 7 May 2021 Assessment period ends 25 June 2021 Semester 1 contact information
Lea Frermann
- Semester 2 - Dual-Delivery
Principal coordinator Lida Rashidi 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 26 July 2021 to 24 October 2021 Last self-enrol date 6 August 2021 Census date 31 August 2021 Last date to withdraw without fail 24 September 2021 Assessment period ends 19 November 2021 Semester 2 contact information
Email: rashidi.l@unimelb.edu.au
Time commitment details
200 hours
Last updated: 3 November 2022
Further information
- Texts
- Subject notes
LEARNING AND TEACHING METHODS
This course is taught over 12 weeks, each week with two one hour formal lectures and a one hour workshop. During the workshops the students are given problems to solve to reinforce the previous week’s lecturing material. The problem solving nature of the workshops is geared for the students to learn and understand the concepts of the subject material.
INDICATIVE KEY LEARNING RESOURCESChristopher D. Manning, Prabhakar Raghavan, and Hinrich Schutze (2008), Information Retrieval, Cambridge University Press. Freely available at informationretrieval.org
Pang-Ning Tan, Michael Steinbach and Vipin Kumar (2005) Introduction to Data Mining, Addison-Wesley.
CAREERS / INDUSTRY LINKS
This subject is relevant to many fields including Engineering, Commerce, Government Organisations, Research Institutes and Institutions in Medicine where data analysis can play a significant improvement in delivering services or improving profits.
- Related Handbook entries
This subject contributes to the following:
Type Name Course Doctor of Philosophy - Engineering Course Ph.D.- Engineering Course Master of Science (Computer Science) Course Master of Data Science Course Master of Commerce (Decision, Risk and Financial Sciences) Course Master of Philosophy - Engineering Specialisation (formal) Computing Specialisation (formal) Software with Business Major Computer Science Specialisation (formal) Distributed Computing Specialisation (formal) Spatial Specialisation (formal) Software Specialisation (formal) Mechatronics - 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.
Please note Single Subject Studies via Community Access Program is not available to student visa holders or applicants
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
Last updated: 3 November 2022