Special Topics in Computing is our place for small, research-led courses taught by ANU experts and visiting scholars. Taking a special topic is a great way to extend your knowledge and start your journey in a research field or community of practice.
These courses cater for later-year undergraduate and postgraduate students looking for further depth in their computing education. Some courses are one-off experiences while others may be coursework under development for our regular curriculum. In any special topics course, you will have the opportunity to work together in a focussed environment with like-minded students and interact with ANU researchers and visitors on highly engaging subject matter.
The curriculum and learning outcomes for each special topic is different, and different topics are offered each semester, see the websites below for information on each course available in the coming semester.
Our special topics courses are offered under the following course codes: COMP3710, COMP4011, COMP4045, COMP4680 (undergraduate) and COMP6470, COMP8011, COMP8045, COMP8650 (postgraduate). See the entries in Programs and Courses for precise course information.
Semester 1, 2026 Courses
COMP2710 GenAI and Programming
Conveners: Nick Barnes and Minh Bui
Pre-req: None
Incompatibilites: Successfully completed or currently enrolled in any COMP-coded course.
This course teaches introductory programming, fundamental programming language and computer science concepts, and computational problem solving illustrated with applications common in science and engineering, such data analysis, visualisation, and image processing. We will take a different approach, including prompting and working with GenAI, with emphasis on testing, debugging and problem decomposition and using GenAI to help understand code. These skills will empower students to write software with the aid of Copilot. Assessment will include exam(s) without the aid of GenAI. Students will also create larger software projects with the aid of GenAI. The course does not require any prior knowledge of programming or computer science.
COMP4680/8650 Generative AI
Convener: Liang Zheng
Pre-Req: 12 units of 3000/6000 and/or 4000 level COMP courses.
Generative AI has been under the spotlight in the machine learning field. This course will focus on two most important topics, large language models for language generation and diffusion models for visual generation. The course will cover their basics, pre-training, post-training, reasoning, agents, etc. Students will experience the state-of-the-art research in this field while gaining their foundational machine learning knowledge.
Semester 2, 2026 Courses
COMP4011/8011 Software Verification using Proof Assistant
Convener: Peter Hoefner
Pre-req: 12 units 3000/6000 level COMP courses and COMP2620/6262 Logic. COMP3610/6361 Principles of Programming Languages not mandatory, but beneficial.
Incompatibility: COMP4011/8011 Software Verification using Proof Assistant (S2-24)
COMP4020/8020 Rapid Prototyping for the Web
Conveners: Charles Martin and Ben Swift:
Pre-req: COMP3900
COMP4045/8045 Virtual Machines and Managed Language Runtimes
Conveners: Tony Hosking and Eduardo Souza
Pre-Req: 12 units 3000/4000 lvl COMP and COMP2310/6310
COMP4620/8620 Adaptive AI
Convener: Jochen Renz
Pre-Req: 12 units 3000/4000 lvl COMP and COMP3620
COMP4620/8620 Planning and Learning for Intelligent Robotics
Convener: Hanna Kurniawati
Pre-Req: 12 units 3000/4000 lvl COMP and COMP3620 or a D or HD in COMP3670/6670.
Incompatible: COMP4620 S2-25 and COMP4680 S2-24.
In short, this class is about sequential decision-making in robotics. Robots have the potential to make society safer and more efficient, from reducing the need for humans to perform dangerous jobs to enhancing services in remote areas to helping busy parents with everyday chores. However, their wide-spread use have often been hindered by the ubiquity of uncertainty. In this class, we will explore and discuss some of the concepts, approaches, and techniques that would enable robots to embrace and work with uncertainty, rather than avoiding them.
We will view robots in a broad sense: Intelligent agents that operate in the physical or simulated physical world and will discuss concepts, basic approaches, and recent scalable approaches of:
- Planning in continuous and hybrid spaces (in contrast to the discrete space planning in COMP3620/6320)
- Sequential decision-making when the effects of actions are uncertain (i.e., Markov Decision Processes)
- Sequential decision-making when the effects of actions are uncertain and the world is only partially observable (i.e., Partially Observable Markov Decision Processes)
- Sequential decision-making when models are unavailable a priori (i.e., Reinforcement Learning and integrated planning and learning)
Enrolment
Enrolment for special topics courses is by permission code. The website for each topic will list pre-requisites, you must apply for the permission code following the process outlined on the CSS website here: Enrolling in CSS courses: ANU College of Systems and Society. Questions about pre-requisites should be sent to CSS Student Services.