Thrive - Next Generation Artificial Intelligence Graduate Program Project - Tal Ellinson

Start year: 2025

Summary: Project Title: Bayesian networks and causal discovery: what school-level policies improve academic outcomes? Project Description: Goals 1.To use Bayesian Networks to find causal links between education practice at the school-level and improved student outcomes. 2.Focus on actionable school-based levers (e.g. curriculum, staff training and explicit instruction) that can be readily translated into education policy and practice. 3.To develop new mathematical tools for identifying the posterior distribution over all graph structures for Directed Acyclic Graphs. Specifically: a.Increase the efficiency of existing accurate methods (e.g. MCMC), to enable exploration of higher-dimensional spaces; and/or b.Discover new gradient-based algorithms for exploring higher-dimensional spaces; and/or c.Quantify the uncertainty (e.g., standard error) of current methods to assess their validity for education policy decision-making.

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.