Course offerings

Our lab is in charge of designing and teaching several courses in the ANU Computer Science cirriculumn.

  • COMP4650/8600 Statistical Machine Learning

    This course provides a broad but thorough intermediate level study of the methods and practices of statistical machine learning, emphasising the mathematical, statistical, and computational aspects. Students will learn how to implement efficient machine learning algorithms on a computer based on principled mathematical foundations. Topics covered will include Bayesian inference and maximum likelihood modelling; regression, classification, density estimation, clustering, principal and independent component analysis; parametric, semi-parametric, and non-parametric models; basis functions, neural networks, kernel methods, and graphical models; deterministic and stochastic optimisation; overfitting, regularisation, and validation.

    See current course info, 2023 course info, 2022 info and 2021 info.

  • COMP4880/8880 Computational Methods for Network Science

    This course covers the essentials of using computational approaches to pose and answer network science research problems. In particular, it covers a selected set of network algorithms in depth. These include random graph models, homophily and friendship paradox, influence and contagion in networks, and network resilience. Furthermore, it also teaches students about the ethics of doing data-driven network science research.
 The course equips the students with in-depth knowledge and hands-on experience in working with network data to study social, biological and cognitive processes. Graduates will be equipped with the technical, theoretical and conceptual skills and knowledge to start a budding career in this field.

    See here for the 2019 Syllabus. Next offering: 2023 or 2024, details TBA.

  • COMP4650/6490 Document Analysis (2015 –)

    This course considers the “document” and its various genres as a fundamental object for business, government and community, such as web pages, social media feeds, news items, and PDF brochures. The goal is to introduce concepts and hands-on tools for automated understanding of large amounts of text. For this, the course covers four broad areas: (A) information retrieval, (B) natural language processing, (C) machine learning for documents, and (D) relevant tools for the web. Tasks include content collection and extraction, formal and informal natural language processing, information extraction, information retrieval, classification and analysis. Fundamental probabilistic techniques for performing these tasks, and some common software systems will be covered, though no area will be covered in great depth.

    See 2018 course schedule and 2018 course information sheet.

    In 2021 this course is re-freshed and ran by Alex Mathews, see course schedule and info sheet.

  • COMP1030 The Art of Computing (2015 – 2017)

    The goal of this course is to teach ANU students from all disciplines computational thinking.

    Computing is transforming business, science and society, making it possible to represent vast amounts of knowledge in digital form (big data) and enabling algorithms to process this knowledge with unprecedented accuracy and speed. Underlying this are the fundamental – and beautiful – ideas of computational thinking: viewing problems and processes through the lens of algorithms and structured data, and tackling complexity through procedural abstractions like iteration and recursion. Students of the course will learn the fundamental skills of applying computational thinking and practical computing, through exploring the impact that computing can have in disciplines such as medical, physical and social sciences. The course offers a breadth and perspective on computing beyond what is provided by focused foundational courses in computer science and other computing-related disciplines.

Guest appearances and outreach

  • Machine Learning in the public sector, training seminar organised by Data to Decisions CRC, July 2017.

  • ANU COMP1140 Research Highlights 2016-2018, “Machine Learning for Online Media”, Lexing Xie

  • ICWSM Science Slam

    From the official description:

    A Science Slam is an epic scientific event where scientists compete with short talks on their research. It’s just like a poetry slam, but with science instead of poems. Slammers are completely free to do whatever they want on stage, everything is allowed including slides, games, the more creative, the better! The only two rules are: The topic of the slam has to be related to social media and the presentation should not take more than 8 minutes.