IFN680 Advanced Machine Learning and Applications
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: | IFN680 |
|---|---|
| Prerequisite(s): | IFN580 or IFQ580 or CAB420 |
| Assumed Knowledge: | Knowledge of a programming language like Python, Java, C# or C is assumed plus Introductory level knowledge of artificial intelligence |
| Credit points: | 12 |
| Timetable | Details in HiQ, if available |
| Availabilities |
|
| CSP student contribution | $1,192 |
| Domestic tuition unit fee | $4,116 |
| International unit fee | $5,616 |
Unit Outline: Semester 2 2026, Gardens Point, Internal
| Unit code: | IFN680 |
|---|---|
| Credit points: | 12 |
| Pre-requisite: | IFN580 or IFQ580 or CAB420 |
| Equivalent: | IFQ680 |
| Assumed Knowledge: | Knowledge of a programming language like Python, Java, C# or C is assumed plus understanding of standard machine learning methods. |
| Coordinator: | Olivier Salvado | olivier.salvado@qut.edu.au |
Overview
This is a specialisation unit in the area of computer science and data analytic. The aim of this unit is to provide you with the knowledge and skills required to design and implement machine learning solutions that can effectively and efficiently solve complex problems. The main advantage of intelligent systems is that they can combine the traditional computer's capacity to remember millions of facts with the human being's cognitive skills, including learning and refining the existing body of knowledge, solving problems with reasoning, helping businesses with strategic planning, diagnosing mechanical faults or human diseases, playing games, and so on. This unit will provide you with an understanding and implementation of the principles and limitations of machine learning techniques that underpins modern Artificial Intelligence.
Learning Outcomes
On successful completion of this unit you will be able to:
- Explain the fundamental theory underpinning various AI and ML techniques and algorithms, and identify their applications and limitations.
- Work independently and in team to implement and apply appropriate AI and ML techniques to solve specific problems, leveraging GenAI capability.
- Critically evaluate, synthesise, and critique the performance, strengths and limitations of AI and ML methods for given problems, leveraging GenAI capability.
- Communicate your results and the limitations of your models professionally with peers and the stakeholder community.
Content
This unit then introduces concepts, models, and algorithms in the areas of:
- Classic machine learning methods
- Deep learning, convolutional neural network, and transformer networks
- Computer vision, including 3D models
- Generative AI, including language models and image generation
- Supervised, unsupervised and reinforcement learning
This unit builds on the prerequisite units covering machine learning (e.g. IFN580 or CAB420). This unit focuses on understanding and implementing key advanced methods. It includes discussion about the performance and limitation of the concepts underlying each methods, both intuitively and formally using mathematics.
Learning Approaches
This unit will be delivered with a theory-to-practice approach. Each week, you will have a 2-hour lecture, which provides you with the theoretical knowledge required for this unit. You will also have a tutorial where you will apply the theory introduced in lectures with programming to solve various problems. You will be guided through the programming problems, with consolidation of how the theory relates to the practical implementation and guided analysis of the results. For the assignments, you will be required to work individually and in pairs to apply the content covered in the lecture and tutorials to new problems or data.
Feedback on Learning and Assessment
Feedback in this unit will be provided in the following ways:
- Formative oral feedback will be offered by the lecturer and tutors during the semester to assist you in the development of your skills.
- Formative written feedback through marking rubric.
- In addition to criteria and standards in a marking rubric, comments on summative assessment will be provided.
- Generic comments will be provided to the cohort through the Canvas.
Teaching staff are available for feedback and advice in the practical sessions.
Assessment
Overview
During this unit, you will build a portfolio of methods implemented in python using pytorch. You will have 7 submissions in total spread over the first half and the second half. Each submission will include coding and a short report to apply machine learning techniques to solve a given problem and communicate your results and design process.
Project portfolio part 1 and 2 also include an oral examination where you are required to answer questions relative to your submissions and relevant content from the lecture and tutorials.
The final examination will allow you to demonstrate the overall knowledge that you obtain from this unit.
Unit Grading Scheme
7- point scale
Assessment Tasks
Assessment: Project portfolio part 1
During the course of the unit, for the main topics covered in the first half of the unit, you will identify and implement existing machine learning algorithms to investigate a hypothesis or apply a method on new data.
You will be assessed on your implementation, performance, and reporting of each of the method (group assessment).
You will be questioned orally about your submissions and related topics (individual assessment).
The ethical and responsible use of generative artificial intelligence (GenAI) tools is permitted for the report and code component but is prohibited during the oral examination. Please refer to the relevant assessment details in Canvas for specific guidelines.
The report and code component is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Project portfolio part 2
During the course of the unit, for the main topics covered in the second half of the unit, you will identify and implement existing machine learning algorithms to investigate a hypothesis or apply a method on new data.
You will be assessed on your implementation, performance, and reporting of each of the method (group assessment).
You will be questioned orally about your submissions and related topics (individual assessment).
The ethical and responsible use of generative artificial intelligence (GenAI) tools is permitted for the report and code component but is prohibited during the oral examination. Please refer to the relevant assessment details in Canvas for specific guidelines.
The report and code component is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Examination (written)
Written quiz with multiple-choice and short answer questions.
The use of generative artificial intelligence (GenAI) tools is prohibited during this assessment.
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.
Requirements to Study
Costs
No extraordinary charges or costs are associated with the requirements for this unit.
Resources
This the recommended main text book for this unit. Plenty of resources (links to on-line resources and publications) will be provided every week, relevant to the week's content.
Resource Materials
Recommended text(s)
Textbook: Deep learning - Foundations and concepts. Bishop and Bishop.
Risk Assessment Statement
There are no unusual health or safety risks associated with this unit
Course Learning Outcomes
This unit is designed to support your development of the following course/study area learning outcomes.IN20 Master of Information Technology
- Demonstrate advanced specialist IT knowledge in at least one information technology discipline.
Relates to: ULO1, Project portfolio part 1, Examination (written) - Critically analyse complex IT problems and opportunities and use creativity and problem-solving skills to generate innovative and novel solutions that are convincingly justified.
Relates to: ULO3, Project portfolio part 1, Project portfolio part 2, Examination (written) - Integrate advanced, industry-best practice, IT methods, tools and techniques to develop and implement complex IT systems, processes and/or software.
Relates to: ULO2, Project portfolio part 1, Project portfolio part 2 - Employ leadership and initiative in both self-directed and collaborative contexts to create value for others.
Relates to: ULO2, Project portfolio part 1, Project portfolio part 2 - Communicate effectively in IT professional and scholarly contexts to specialist and non-specialist audiences using written, visual and oral formats.
Relates to: ULO4, Project portfolio part 1, Project portfolio part 2
IN28 Master of Artificial Intelligence
- Demonstrate advanced specialist IT knowledge in Artificial Intelligence discipline.
Relates to: Project portfolio part 1, Examination (written) - Critically analyse complex Artificial Intelligence problems and opportunities and use creativity and problem-solving skills to generate innovative and novel solutions that are convincingly justified.
Relates to: Project portfolio part 1, Project portfolio part 2 - Integrate advanced, industry-best practice, Artificial Intelligence methods, tools and techniques to develop and implement complex Artificial Intelligence systems, processes and/or software.
Relates to: Project portfolio part 1, Project portfolio part 2 - Demonstrate knowledge of Artificial Intelligence research principles and methods and their application to Artificial Intelligence focused, real-world scholarly or professional projects.
Relates to: Project portfolio part 1, Project portfolio part 2 - Employ leadership and initiative in both self-directed and collaborative contexts to create value for others.
Relates to: Examination (written)