Date: October 28, 2025 (Tue)
Time: 11:00am – 12:00pm
Venue: P603 IDS Office, Graduate House, HKU
Speaker:
Prof Frederick Eberhardt, Professor of Philosophy, California Institute of Technology
Moderator:
Prof Boris Babic, Dept of Philosophy & Law (by courtesy), HKU
Abstract:
Causal representations are models of real-world data that retain causal information, so in particular, they provide information about how a system will respond when subject to experimental intervention. While there is an extensive literature on how to discover the causal relations among a given set of variables, it is much less clear how to identify and construct the causal variables in the first place. Yet, given the vast amounts of measurement and sensor data available today, identifying the causal quantities has become just as important as identifying the relations between them. This presentation will focus on one approach, Causal Feature Learning, that learns a macro level causal representation from micro level measurement data. Time permitting, we will illustrate the method with applications in climate science, economics and neuroscience.
Host: HKU Musketeers Foundation – Institute of Data Science
Co-Host: AI & Humanity Lab, Department of Philosophy, HKU
