MXB301 Advanced Mathematical Techniques in Artificial Intelligence
To view more information for this unit, select Unit Outline from the list below. Please note the teaching period for which the Unit Outline is relevant.
| Unit code: | MXB301 |
|---|---|
| Prerequisite(s): | MXB103 and MXB105 and MXB201 |
| Credit points: | 12 |
| Timetable | Details in HiQ, if available |
| Availabilities |
|
| CSP student contribution | $592 |
| Domestic tuition unit fee | $3,816 |
| International unit fee | $4,872 |
Unit Outline: Semester 2 2026, Gardens Point, Internal
| Unit code: | MXB301 |
|---|---|
| Credit points: | 12 |
| Pre-requisite: | MXB103 and MXB105 and MXB201 |
| Coordinator: | Timothy Moroney | t.moroney@qut.edu.au |
Overview
This is an advanced unit on mathematical techniques underpinning modern Artificial Intelligence systems. Although there are many technologies that can reasonably be considered to exhibit “artificial intelligence”, there is a common set of mathematical foundations that power the remarkable advances in these systems in the last decade. Modern AI systems are built from very large models with extraordinary numbers of trainable parameters, and an objective function that measures the model’s performance on a vast set of training data. Depending on the application, this data may comprise text, audio, images, or more complex data. AI systems “learn” from the data through an iterative process of adjusting its parameters to improve its performance, as measured by the objective function. That such a colossal optimisation problem is even practical, let alone these days routine, represents arguably the greatest modern triumph of the techniques of calculus, linear algebra and probability.
Learning Outcomes
On successful completion of this unit you will be able to:
- Demonstrate knowledge of foundational mathematical techniques underpinning modern Artificial Intelligence systems and algorithms.
- Critically evaluate, synthesise, and critique the performance, strengths and limitations of Artificial Intelligence frameworks for given problems.
- Critically select and implement appropriate computational algorithms in computer software, including the use of specialised data structures, to solve practical problems.
- Engage communication skills through a combination of report writing, code documentation, and individual problem-solving.
- Demonstrate good teamwork practices through collaborative activities in a group environment.
- Utilise an online portfolio for evidencing skill development to enhance future career opportunities.
- Critically apply Generative AI tools to the task of translating the implementation of an algorithm from one programming language to another.
Content
Matrix calculus, multidimensional chain rules, forward and reverse mode automatic differentiation, back propagation, gradient descent, Newton’s method, Quasi-Newton methods, line search and trust regions, regularisation, momentum-based methods, stochastic optimisation, case studies in AI. Aspects of sustainability will be considered through the context of energy consumption of AI systems relating to algorithmic cost.
Learning Approaches
This unit involves lectures and practicals in which you will engage in collaborative activity with peers and teaching staff. The material presented will be context-based utilising examples relevant to a range of artificial intelligence applications. You will utilise technology to assist with solving and visualising key concepts to aid in your understanding.
You can be expected to spend 10 - 15 hours per week attending classes, completing assessment tasks and undertaking independent study to consolidate your learning.
The emphasis will be on active learning, that is, enhancing your learning by doing activities, encouraging both individual and collaborative learning, developing your written and oral communication skills and your attitudes to promote your life-long learning.
Particularly for your group-based modelling assessment activity, you will work with peers and with teaching staff to develop effective methods and approaches for communicating, evaluating and presenting information, and you will learn how to work effectively within groups with consideration for in-person and remote interactions.
Feedback on Learning and Assessment
Formative feedback will be provided for the in-semester assessment items through written comments on the assessment items, student perusal of the marked assessment piece, and informal interview as required.
Summative feedback will be provided throughout the semester with progressive results posted on Canvas.
Assessment
Overview
The assessment items in this unit are designed to determine your level of competency in meeting the unit learning outcomes while providing you with a range of tasks with varying levels of skill development and difficulty.
Unit Grading Scheme
7- point scale
Assessment Tasks
Assessment: Portfolio
The portfolio is comprised of a number of notebook-based worksheets where you will implement the techniques discussed in lectures using relevant computer software. There will be two submission dates in Weeks 5 and 12 of the semester, with each submission contributing 10% to your final grade. For the first submission date, you choose two worksheets to submit out of Practicals 1-4. For the second submission date, you choose two worksheets to submit out of Practicals 5-8.For each worksheet you need to complete the specified tasks and insert all code and your reasoning into the worksheet.
A required component of the portfolio will be critically applying Generative AI tools to the task of translating the implementation of an algorithm from one programming language to another.
The ethical and responsible use of generative artificial intelligence (GenAI) tools is authorised in this assessment. See the relevant assessment details in Canvas for specific guidelines.
This assignment is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Case Study
In this case study, you will analyse and implement appropriate mathematical techniques in the context of AI models to solve a given real-world problem. You will detail the process of analysis and implementation of techniques, investigate and compare different methods for its solution, and present your findings in a report.
You will investigate the adaption of advanced mathematical techniques and their cross-over into modern AI-related issues such as sustainable energy use as an authentic and interdisciplinary experience.
This assessment item will contribute to your online portfolio of work with an authentic demonstration of your prowess in applying advanced mathematical techniques to applications in AI, thereby enhancing your career development and employability.
The ethical and responsible use of generative artificial intelligence (GenAI) tools is authorised in this assessment. See the relevant assessment details in Canvas for specific guidelines.
This assignment is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Exam
This final invigilated examination will assess your learning over the course of the entire semester.
The use of generative artificial intelligence (GenAI) tools is prohibited during this assessment.
The examination will require attendance on QUT campus.
Academic Integrity
Academic integrity is a commitment to undertaking academic work and assessment in a manner that is ethical, fair, honest, respectful and accountable.
The Academic Integrity Policy sets out the range of conduct that can be a failure to maintain the standards of academic integrity. This includes, cheating in exams, plagiarism, self-plagiarism, collusion and contract cheating. It also includes providing fraudulent or altered documentation in support of an academic concession application, for example an assignment extension or a deferred exam.
You are encouraged to make use of QUT’s learning support services, resources and tools to assure the academic integrity of your assessment. This includes the use of text matching software that may be available to assist with self-assessing your academic integrity as part of the assessment submission process.
Breaching QUT’s Academic Integrity Policy or engaging in conduct that may defeat or compromise the purpose of assessment can lead to a finding of student misconduct (Code of Conduct – Student) and result in the imposition of penalties under the Management of Student Misconduct Policy, ranging from a grade reduction to exclusion from QUT.
Resources
All learning materials will be made available via the Canvas unit site. There is no set text for this unit.
Risk Assessment Statement
There are no out of the ordinary risks associated with this unit, as all classes will be held in ordinary lecture theatres. Emergency exits and assembly areas will be pointed out in the first few lectures. You are referred to the University policy on health and safety.
http://www.mopp.qut.edu.au/A/A_09_01.jsp
Course Learning Outcomes
This unit is designed to support your development of the following course/study area learning outcomes.MS01 Bachelor of Mathematics
- Demonstrate a broad and coherent knowledge of the principles, concepts and techniques of the applied mathematical sciences, with depth in at least one area.
Relates to: Portfolio, Exam - Formulate and model problems in mathematical terms and apply appropriate mathematical, statistical and computational techniques to solve practical and abstract problems.
Relates to: Portfolio, Exam - Demonstrate aptitude in computer programming, and familiarity with industry-leading programming languages and relevant specialised mathematical, statistical and generative artificial intelligence software and tools.
Relates to: Portfolio, Case Study, Exam - Demonstrate critical thinking and problem solving skills across a range of applied mathematical and statistical contexts, and adaptivity in applying learned techniques in new or unfamiliar contexts.
Relates to: Case Study - Present information and articulate arguments and conclusions in a variety of modes, to diverse audiences both expert and non-expert.
Relates to: Case Study - Work both independently and collaboratively in diverse teams, including cross-cultural and cross-disciplinary teams.
Relates to: Case Study - Demonstrate awareness of the social and ethical frameworks within which mathematics and statistics are practised, including their relation to Indigenous Australians and their impact on sustainability.
Relates to: Case Study, Exam
MV01 Bachelor of Mathematics
- Demonstrate a broad and coherent knowledge of the principles, concepts and techniques of the applied mathematical sciences, with depth in at least one area.
Relates to: Portfolio, Exam - Formulate and model problems in mathematical terms and apply appropriate mathematical, statistical and computational techniques to solve practical and abstract problems.
Relates to: Portfolio, Exam - Demonstrate aptitude in computer programming, and familiarity with industry-leading programming languages and relevant specialised mathematical, statistical and generative artificial intelligence software and tools.
Relates to: Portfolio, Case Study, Exam - Demonstrate critical thinking and problem solving skills across a range of applied mathematical and statistical contexts, and adaptivity in applying learned techniques in new or unfamiliar contexts.
Relates to: Case Study - Present information and articulate arguments and conclusions in a variety of modes, to diverse audiences both expert and non-expert.
Relates to: Case Study - Work both independently and collaboratively in diverse teams, including cross-cultural and cross-disciplinary teams.
Relates to: Case Study - Demonstrate awareness of the social and ethical frameworks within which mathematics and statistics are practised, including their relation to Indigenous Australians and their impact on sustainability.
Relates to: Case Study, Exam