ENN585 Advanced Machine Learning
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: | ENN585 |
|---|---|
| Prerequisite(s): | (ENN582 or CAB320) and ENN583 |
| Credit points: | 12 |
| Timetable | Details in HiQ, if available |
| Availabilities |
|
| CSP student contribution | $1,118 |
| Domestic tuition unit fee | $3,528 |
| International unit fee | $4,824 |
Unit Outline: Semester 1 2024, Gardens Point, Internal
| Unit code: | ENN585 |
|---|---|
| Credit points: | 12 |
| Pre-requisite: | ENN582 and ENN583 |
| Coordinator: | Niko Suenderhauf | niko.suenderhauf@qut.edu.au |
Overview
Building on the foundational units for machine learning, reinforcement learning, and robotic vision, this unit covers advanced topics in machine learning.
Topics include deep imitation and reinforcement learning, probabilistic machine learning approximations, transformers, generative machine learning including diffusion models, as well as large language and vision-language models and their applications in robotics. Example applications will focus on robotic vision and control domains.
The unit also discusses the ethical principles and techniques that inform the development and responsible use of artificial intelligence technology.
Learning Outcomes
On successful completion of this unit you will be able to:
- Research and recommend machine learning approaches to address complex real-world robotic challenges
- Interpret, adapt and apply advanced machine learning methods to solve complex robotic vision and control problems
- Critically analyse, synthetise and review cutting edge developments in machine learning
- Critically analyse and communicate the performance of advanced machine learning systems for robotics
Content
The following topics will be covered in this unit:
- Deep Reinforcement Learning
- Imitation Learning
- Uncertainty and Probabilistic Aspects of Deep Learning
- Transformers
- Large Language Models, Vision-Language Models, Multimodal Models
- Efficient Training of Transformers
- Generative Models and Diffusion Models
- Applications of Large Language and Vision-Language Models in Robotics
- Emerging Technologies
Throughout the unit, we will weave in discussions of the principles of ethics in AI.
Learning Approaches
You can expect the following activities in this unit:
- Lectures that present key concepts, methods, and algorithms and offer a chance for in-depth discussion
- Practical sessions where you will be engaged in collaborative activity with peers and tutors, that will provide opportunities to explore the underlying theory, practice in the application of theory and algorithms, and allow exploration of concepts with tutors and other students.
- Write research/survey papers on selected real-world topics
- Practical implementation of selected real-world topics
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 criteria sheet grading.
- 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 lab sessions.
Assessment
Overview
Assessment in this unit will include three online quizzes to assess the unit learning outcomes; written formal research project reports, and project demonstrations.
Unit Grading Scheme
7- point scale
Assessment Tasks
Assessment: Project 1
In this project, you will design and implement a solution to a complex robotic control problem and report on the system's performance. You will be assessed based on the performance of your solution, an oral presentation where you justify your design and analyse performance, and your response to questions from the teaching team.
Assessment: Project 2
In this project, you will design and implement a solution to a complex robotic perception problem and report on the system's performance. You will be assessed based on the performance of your solution, an oral presentation where you justify your design and analyse performance, and your response to questions from the teaching team.
Assessment: Literature Review, Interpretation and Reflection
Throughout the semester, you will review research papers, interpreting how they build on fundamental concepts and reflect on trends in the research literature of selected topics. You will share a short discussion with your peers in an online forum to collaboratively analyse the literature.
Academic Integrity
Students are expected to engage in learning and assessment at QUT with honesty, transparency and fairness. Maintaining academic integrity means upholding these principles and demonstrating valuable professional capabilities based on ethical foundations.
Failure to maintain academic integrity can take many forms. It includes cheating in examinations, plagiarism, self-plagiarism, collusion, and submitting an assessment item completed by another person (e.g. contract cheating). It can also include providing your assessment to another entity, such as to a person or website.
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.
Further details of QUT’s approach to academic integrity are outlined in the Academic integrity policy and the Student Code of Conduct. Breaching QUT’s Academic integrity policy is regarded as student misconduct and can lead to the imposition of penalties ranging from a grade reduction to exclusion from QUT.
Resources
There is no required text book. Contents from latest publications in top-tier machine learning journals will be used and referenced during the lectures.
Learning material in this unit will be managed from the units Canvas page.
Risk Assessment Statement
You will undertake lectures and practicals in a traditional classroom and computer laboratory. There are no extraordinary workplace health and safety issues associated with these components of the unit.
Course Learning Outcomes
This unit is designed to support your development of the following course/study area learning outcomes.EN52 Master of Robotics and Artificial Intelligence
- Demonstrate and apply advanced and specialist discipline knowledge, concepts and practices in Robotics and AI
Relates to: Project 1, Literature Review, Interpretation and Reflection - Critically analyse, evaluate and apply appropriate methods to Robotics and AI problems to achieve research-informed solutions
Relates to: Project 2, Literature Review, Interpretation and Reflection - Apply systematic approaches to plan, design, execute and manage projects in Robotics and AI
Relates to: Project 2, Literature Review, Interpretation and Reflection - Communicate complex information effectively and succinctly in oral and written form for diverse purposes and audiences
Relates to: Project 2, Literature Review, Interpretation and Reflection - Work independently and collaboratively demonstrating ethical and socially responsible practice
Relates to: Project 2, Literature Review, Interpretation and Reflection
EN72 Master of Advanced Robotics and Artificial Intelligence
- Demonstrate and apply advanced and specialist discipline knowledge, concepts and practices in Advanced Robotics and AI and Data Analytics domains
Relates to: Project 1, Literature Review, Interpretation and Reflection - Critically analyse, evaluate and apply appropriate methods to problems to achieve research-informed solutions in Advanced Robotics and AI and Data Analytics domains
Relates to: Project 2, Literature Review, Interpretation and Reflection - Apply systematic approaches to plan, design, execute and manage projects in Advanced Robotics and AI and Data Analytics domains
Relates to: Project 2, Literature Review, Interpretation and Reflection - Communicate complex information effectively and succinctly in oral and written form for diverse purposes and audiences
Relates to: Project 2, Literature Review, Interpretation and Reflection - Work independently and collaboratively demonstrating ethical and socially responsible practice
Relates to: Project 2, Literature Review, Interpretation and Reflection
EN79 Graduate Diploma in Engineering Studies
- Demonstrate and apply advanced discipline knowledge, concepts and practices as they relate to contemporary Engineering practice
Relates to: Project 1, Literature Review, Interpretation and Reflection - Analyse and evaluate Engineering problems using technical approaches informed by contemporary practice and leading edge research to achieve innovative, critically informed solutions
Relates to: Project 2, Literature Review, Interpretation and Reflection - Apply innovative, systematic approaches to plan, design, deliver and manage Engineering projects in a way that assures sustainable outcomes over their whole lifecycle
Relates to: Project 2, Literature Review, Interpretation and Reflection - Effectively communicate Engineering problems, related complex data and information, and solutions in contemporary professional formats for diverse purposes and audiences
Relates to: Project 2, Literature Review, Interpretation and Reflection - Demonstrate ethically and socially responsible practice, recognising the importance of personal accountability and reflective practice when working in individual and collaborative modes
Relates to: Project 2, Literature Review, Interpretation and Reflection