Hi! I’m a PhD Student in the Waterloo Intelligent Systems Lab (WISELab) at the University of Waterloo. I am broadly interested in creating embodied autonomous agents and systems. My PhD work focuses chiefly on motion prediction and planning tasks for self-driving vehicles, and especially how to tackle the problems of covariate shift and casual confusion that hamper closed-loop performance of popular methods.
We propose a new general methodology, Explainer Divergence Scores (EDS), to evaluate Post-Hoc Explanations for the purpose of identifying spurious correlations in neural networks. We use our methodology to compare the detection performance of three different explainers - feature attribution methods, influential examples and concept extraction, on two different image datasets.