Scholarship applications for this project have now closed
About the Project
Deep neural networks (DNNs) are limited in their capacity to safely assist scientific discovery and decision making until a particular pitfall is addressed. While DNNs succeed in exploiting non-linear patterns in very large and high-dimensional datasets, they catastrophically fail without warning under dataset shift, i.e., changes in data distribution. This project, in collaboration with Max Kelsen P/L, will study various ways to resolve this pitfall by characterising, detecting, and generalising against dataset shift. The research will theoretically unify sparse and inconsistent literature, and empirically validate that theory in the application of genomics, with results to inform ways to maximise reliability of learning systems under datasets shifts.
About the Candidate
The ARC Training Centre for Information Resilience (CIRES) invites highly motivated and committed candidates to apply for a fully funded PhD position focused on developing techniques and methodologies grounded in unsolved challenges in computational biology and multi-modal healthcare data. In line with CIRES’s industry engagement objectives, the position is defined and co-funded in close collaboration with the highly successful Brisbane-based consultancy – Max Kelsen. The candidate will investigate the proposed methodologies on real datasets from different healthcare organizations, co-supervised by Max Kelsen Partner Investigator Dr Maciej Trzaskowski, an expert in machine learning and quantum computing.
Max Kelsen has active research, development, and consulting activities in the ﬁelds of AI and cancer genomics, and has prioritized AI safety as a key ingredient of any new product prior to deployment. This scholarship is one of two CIRES projects with Max Kelsen related to organisational and transformational aspects of data, algorithms, and AI.
The successful candidate is expected to have good understanding of concepts from applied statistics/probability, numerical linear algebra, and machine learning. Proficiency in Python programming language and machine learning software packages such as Pytorch is required.