AI, ML and Friends is a weekly seminar series within the School of Computing on Artificial Intelligence, Machine Learning, and related topics. We are open to attendees and presenters external to the school. Please sign up to the mailing list to receive weekly announcements including zoom details, and email the seminar organiser to schedule a talk.

Upcoming Seminars

29 January 2026, 11:00#

Explainable Neuro-Symbolic AI for Automated Grading of Physics Exams#

Speaker: Lachlan McGinness

Abstract: This talk presents AlphaPhysics, a neuro-symbolic system that combines explainable machine learning, term rewriting, and large language models to automatically grade physics examinations. The approach aims to achieve accurate, transparent assessment while significantly reducing teacher workload in high-stakes educational settings.

Bio: Lachlan McGinness is a PhD candidate in Computer Science at the Australian National University and CSIRO, working at the intersection of artificial intelligence and physics education. His research focuses on explainable neuro-symbolic methods for automatically grading complex physics exam responses.

Where: Building 145, room 3.41

12 February 2026, 11:00#

Endogenous Price Discovery and Emergent Dynamics in Financial Markets — An Agent-Based Investigation#

Speaker: Patrick Liston

Abstract: This talk presents research investigating financial markets as complex adaptive systems through the lens of agent-based simulation. I demonstrate how market fragility and “flash crashes” can be replicated using fully synthetic simulation methods, without reliance on exogenous historical price data. I will introduce two custom simulators, SIMP and CHAD, which are uniquely capable of modelling these dynamics. By employing these frameworks, my research replicates fragility and flash crashes—phenomena not previously studied through this specific lens of endogenous, dual-book liquidity. A key focus is on the role of stop-loss orders; the presentation illustrates how these mechanisms precipitate cascades, providing a mechanistic notion of how structural fragility emerges in modern digital asset markets.

Bio: Patrick Liston is a PhD candidate at the Australian National University, researching the emergent behaviour of financial markets as complex adaptive systems. His work spans the development of synthetic market environments and the evaluation of adaptive trading agents. He has published research on market fragility, liquidity shocks, and pattern-based algorithmic trading at venues such as ICAIF, AAAI, AJCAI, and ICAART.

Where: Building 145, room 1.33

19 February 2026, 11:00#

Machine learning for flow cytometry: the present, the opportunities, the challenges#

Speaker: Zora Zhuang

Abstract: Flow cytometry characterises cells through noisy, partial observations of the cell surface, generating medium-resolution cellular features in an affordable manner. More recently, deep learning methods have been deployed to link cellular patterns in flow cytometry to complex patient conditions, to various degrees of success. In this talk, we’ll discuss both the potentials and the limitations of flow cytometry data, the challenges they present to ML based methods, and a new approach that could utilise flow data more effectively.

Bio: Zora Zhuang is a SoCo PhD candidate and a member of the Andrews group in JCSMR. She works in the intersection of machine learning and biology, developing practical machine learning strategies for flow cytometry data, with eventual clinical applications in mind.