Course coordinator
Dr Xin Yu
Course overview
- Study period
- Semester 2, 2024 (22/07/2024 - 18/11/2024)
- Study level
- Postgraduate Coursework
- Location
- St Lucia
- Attendance mode
- In Person
- Units
- 2
- Administrative campus
- St Lucia
- Coordinating unit
- Elec Engineering & Comp Science School
Machine learning is a branch of artificial intelligence concerned with the development and application of adaptive algorithms that use example data or previous experience to solve a given problem. Topics include: learning problems (e.g regression, classification, unsupervised) and theory, neural networks, statistical and probabilistic models, clustering, ensembles, implementation issues, applications (e.g. bioinformatics, cognitive science, forecasting, robotics, signal and image processing).
Machine learning is a rapidly growing field at the intersection of computer science and statistics that is concerned with finding patterns in data. It is responsible for tremendous advances in technology, from personalized product recommendations to speech recognition in cell phones.
The goal of this course is to provide a solid intuitive understanding of the main tools and concepts of Machine Learning coupled with significant hands-on experience. The emphasis will be on intuition and practical examples rather than theoretical results, although a good understanding of probability, statistics, calculus and linear algebra will be important. The development of group skills on machine learning projects will be a learning objective of this course.
Each lecture will be grounded in one specific and practical case-study, for example predicting stock values using regression. At the end of this course, you will master core skills and knowledge on how to analyse sentiment from user reviews, retrieve documents of interest, predict house prices based on house-level features, recommend products, and search for images. You will understand how the most common Machine Learning methods work, how to apply them to new problems, run evaluations and interpret results, and think about scaling up from thousands to billions of data points. Together, this will form an understanding of the Machine Learning pipeline needed to develop and deploy practical intelligent applications.
Course requirements
Assumed background
The course will cover concepts and material that assumes knowledge of algorithms and data structures, mathematics, statistics and probability appropriate for a coursework masters student.
Prerequisites
You'll need to complete the following courses before enrolling in this one:
CSSE7030 and MATH7501 and STAT7203
Incompatible
You can't enrol in this course if you've already completed the following:
COMP4702 or COMP7703
Restrictions
Restricted to MDataSc students only.
Course contact
Course staff
Lecturer
Dr Xin Yu
Dr Nan Ye
Timetable
The timetable for this course is available on the UQ Public Timetable.
Additional timetable information
Note: Practical and Tutorial sessions will commence in week 2 of the course.
Aims and outcomes
Students will gain a fundamental understanding of a wide range of Machine Learning techniques and algorithms, including supervised and unsupervised learning. Students will also gain an appreciation for the practical applications of machine learning techniques, and will gain experience in implementation and using machine learning methods.
Learning outcomes
After successfully completing this course you should be able to:
LO1.
Describe the core theoretical and conceptual frameworks that are used in Machine Learning.
LO2.
Explain the properties and functions of a range of different Machine Learning models and to be able to connect a model to appropriate theoretical foundations.
LO3.
Formulate an algorithm that instantiates a given Machine Learning model using appropriate data.
LO4.
Implement Machine Learning algorithms in a high-level programming language.
LO5.
Formulate and execute experiments with implemented Machine Learning techniques on data sets, and to evaluate and reflect on the results.
LO6.
Explain the relationships between the different types of techniques used in Machine Learning and the relationships between Machine Learning and other disciplines.
LO7.
Recognize potential real-world applications of Machine Learning and evaluate the suitability of different Machine Learning technique implementations, algorithms, models and theory for a given application.
LO8.
Carry out complex, collaborative machine learning projects as part of a team.
Assessment
Assessment summary
| Category | Assessment task | Weight | Due date |
|---|---|---|---|
| Tutorial/ Problem Set | Assignment 1 | 15% |
16/08/2024 3:00 pm |
| Tutorial/ Problem Set | Assignment 2 | 15% |
4/10/2024 3:00 pm |
| Project |
Group Project
|
40% |
Proposal Deadline 13/09/2024 3:00 pm Presentation Seminar 25/10/2024 3:00 pm Final Report Deadline 15/11/2024 3:00 pm |
| Examination |
Final Exam
|
30% |
End of Semester Exam Period 2/11/2024 - 16/11/2024 |
A hurdle is an assessment requirement that must be satisfied in order to receive a specific grade for the course. Check the assessment details for more information about hurdle requirements.
Assessment details
Assignment 1
- Mode
- Written
- Category
- Tutorial/ Problem Set
- Weight
- 15%
- Due date
16/08/2024 3:00 pm
- Learning outcomes
- L01, L02, L03, L04
Task description
Each assignment will consist of a number of hand written tasks as well as implementation exercises based on topics covered in preceding lectures, tutorials and pracs.
Assignments to be completed individually.
Submission guidelines
Online Submission
Deferral or extension
You may be able to apply for an extension.
The maximum extension allowed is 7 days. Extensions are given in multiples of 24 hours.
Marked assignments with feedback and/or detailed solutions with feedback will be released to students within 14 - 21 days.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Assignment 2
- Mode
- Written
- Category
- Tutorial/ Problem Set
- Weight
- 15%
- Due date
4/10/2024 3:00 pm
- Learning outcomes
- L05, L06, L07, L08
Task description
Each assignment will consist of a number of hand written tasks as well as implementation exercises based on topics covered in preceding lectures, tutorials and pracs.
Assignments to be completed individually.
Submission guidelines
Online Submission
Deferral or extension
You may be able to apply for an extension.
The maximum extension allowed is 7 days. Extensions are given in multiples of 24 hours.
Marked assignments with feedback and/or detailed solutions with feedback will be released to students within 14 - 21 days.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Group Project
- Team or group-based
- Mode
- Oral, Written
- Category
- Project
- Weight
- 40%
- Due date
Proposal Deadline 13/09/2024 3:00 pm
Presentation Seminar 25/10/2024 3:00 pm
Final Report Deadline 15/11/2024 3:00 pm
- Learning outcomes
- L01, L02, L03, L04, L05, L06, L07, L08
Task description
Course group project. To be done in groups of 4-5 students.
Submission guidelines
Deferral or extension
You may be able to apply for an extension.
Proposal
Maximum Extension Length: 7 calendar days. This course uses a progressive assessment approach, where feedback and/or detailed solutions will be released to students within 14-21 days
Late Penalty: Assessment items received after the deadline will be subject to a late penalty of 10% per 24 hours of the maximum possible mark for the assessment item. More than 7 periods of 24 hours, 100% penalty.
Presentation Seminar
Maximum Extension Length: 0 Days. Oral sessions or Demo sessions scheduled with multiple markers and is time limited. Extension impacts on other students in team.
Late Penalty: 100% Late Penalty
Final Report
Maximum Extension Length: 7 calendar days. This course uses a progressive assessment approach, where feedback and/or detailed solutions will be released to students within 14-21 days
Late Penalty: Assessment items received after the deadline will be subject to a late penalty of 10% per 24 hours of the maximum possible mark for the assessment item. More than 7 periods of 24 hours, 100% penalty.
Final Exam
- Hurdle
- Mode
- Written
- Category
- Examination
- Weight
- 30%
- Due date
End of Semester Exam Period
2/11/2024 - 16/11/2024
- Learning outcomes
- L01, L02, L03, L04, L05, L06, L07, L08
Task description
This will be a closed-book invigilated final exam covering all material from the course.
Hurdle requirements
If less than 50% of marks for the final exam is attained, the student's grade for the course will be capped at 3.Exam details
| Planning time | 10 minutes |
|---|---|
| Duration | 120 minutes |
| Calculator options | (In person) Casio FX82 series only or UQ approved and labelled calculator |
| Open/closed book | Closed Book examination - no written materials permitted |
| Exam platform | Paper based |
| Invigilation | Invigilated in person |
Submission guidelines
Deferral or extension
You may be able to defer this exam.
Course grading
Full criteria for each grade is available in the Assessment Procedure.
| Grade | Cut off Percent | Description |
|---|---|---|
| 1 (Low Fail) | 0 - 19 |
Absence of evidence of achievement of course learning outcomes. Course grade description: This grade will be awarded when the combined total marks from all assessment is at least 0% but less than 20% of total marks available |
| 2 (Fail) | 20 - 44 |
Minimal evidence of achievement of course learning outcomes. Course grade description: This grade will be awarded when the combined total marks from all assessment is at least 20% but less than 45% of total marks available. |
| 3 (Marginal Fail) | 45 - 49 |
Demonstrated evidence of developing achievement of course learning outcomes Course grade description: This grade will be awarded when the combined total marks from all assessment is at least 45% but less than 50% of total marks available. |
| 4 (Pass) | 50 - 64 |
Demonstrated evidence of functional achievement of course learning outcomes. Course grade description: This grade will be awarded when the combined total marks from all assessment is at least 50% but less than 65% of total marks available. |
| 5 (Credit) | 65 - 74 |
Demonstrated evidence of proficient achievement of course learning outcomes. Course grade description: This grade will be awarded when the combined total marks from all assessment is at least 65% but less than 75% of total marks available. |
| 6 (Distinction) | 75 - 84 |
Demonstrated evidence of advanced achievement of course learning outcomes. Course grade description: This grade will be awarded when the combined total marks from all assessment is at least 75% but less than 85% of total marks available. |
| 7 (High Distinction) | 85 - 100 |
Demonstrated evidence of exceptional achievement of course learning outcomes. Course grade description: This grade will be awarded when the combined total marks from all assessment is greater than 85% of total marks available. |
Additional course grading information
These percentages will be rounded to the nearest integer before any grade cut-offs apply.
If less than 50% of marks for the final exam is attained, the student's grade for the course will be capped at 3.
Group marks may vary depending on individual performance/contribution. This could be peer assessment and/or a moderation process. The course coordinator reserves the right to vary group marks for each group member in the event of varied contributions to the team effort.
Supplementary assessment
Supplementary assessment is available for this course.
Additional assessment information
Use of Generative AI for the Assessment in this Course
- Final exam: This assessment task is to be completed in-person. The use of Artificial Intelligence (AI) tools will not be permitted. Any attempted use of AI may constitute student misconduct under the Student Code of Conduct.
- Assignments: Artificial Intelligence (AI) provides emerging tools that may support students in completing this assessment task. Students may appropriately use AI in completing this assessment task. Students must clearly reference any use of AI in each instance. A failure to reference AI use may constitute student misconduct under the Student Code of Conduct.
- Group project: Artificial Intelligence (AI) provides emerging tools that may support students in completing this assessment task. Students may appropriately use AI in completing this assessment task. Students must clearly reference any use of AI in each instance. A failure to reference AI use may constitute student misconduct under the Student Code of Conduct.
Having Troubles?
If you are having difficulties with any aspect of the course material you should seek help. Speak to the course teaching staff.
If external circumstances are affecting your ability to work on the course, you should seek help as soon as possible. The University and UQ Union have organisations and staff who are able to help, for example, UQ Student Services are able to help with study and exam skills, tertiary learning skills, writing skills, financial assistance, personal issues, and disability services (among other things).
Complaints and criticisms should be directed in the first instance to the course coordinator. If you are not satisfied with the outcome, you may bring the matter to the attention of the School of EECS Director of Teaching and Learning.
Learning resources
You'll need the following resources to successfully complete the course. We've indicated below if you need a personal copy of the reading materials or your own item.
Library resources
Find the required and recommended resources for this course on the UQ Library website.
Additional learning resources information
Additional resources (e.g. journal and conference papers, web sites) may be referred to during classes.
Learning activities
The learning activities for this course are outlined below. Learn more about the learning outcomes that apply to this course.
Filter activity type by
Please select
| Learning period | Activity type | Topic |
|---|---|---|
Multiple weeks From Week 1 To Week 13 |
Lecture |
Lectures 1. Introduction; 2. Linear Regression; 3. PCA & LDA; 4. Classification; 5. Clustering and Similarity; 6. Support Vector Machines & Kernel Methods. 7. Ensemble Methods: Random Forest and Boosting; 8. The Perceptron; 9. Convolutional Neural Networks; 10. Adversarial Examples; 11. Interpreting Machine Learning Algorithms; 12. Bayesian; 13. Course Summary/Overview Learning outcomes: L01, L02, L03, L04, L05, L06, L07, L08 |
Multiple weeks From Week 2 To Week 12 |
Tutorial |
Tutorials 2. Linear Regression; 3. PCA & LDA; 4. Classification; 5. Clustering and Similarity; 6. Support Vector Machines & Kernel Methods. 7. Ensemble Methods: Random Forest and Boosting; 8. The Perceptron; 9. Convolutional Neural Networks; 10. Adversarial Examples; 11. Interpreting Machine Learning Algorithms; 12. Bayesian; Learning outcomes: L01, L02, L06, L07 |
Practical |
Practicals 2. Linear Regression; 3. PCA & LDA; 4. Classification; 5. Clustering and Similarity; 6. Support Vector Machines & Kernel Methods. 7. Ensemble Methods: Random Forest and Boosting; 8. The Perceptron; 9. Convolutional Neural Networks; 10. Adversarial Examples; 11. Interpreting Machine Learning Algorithms; 12. Bayesian Learning outcomes: L03, L04, L05, L08 |
Additional learning activity information
Monday in Week 11 is a public holiday.
Policies and procedures
University policies and procedures apply to all aspects of student life. As a UQ student, you must comply with University-wide and program-specific requirements, including the:
- Student Code of Conduct Policy
- Student Integrity and Misconduct Policy and Procedure
- Assessment Procedure
- Examinations Procedure
- Reasonable Adjustments - Students Policy and Procedure
Learn more about UQ policies on my.UQ and the Policy and Procedure Library.
School guidelines
Your school has additional guidelines you'll need to follow for this course: