Sara Hooker

A Tale Of Two Long Tails

2021 · arXiv (Cornell University)

As machine learning models are increasingly employed to assist human decision-makers, it becomes critical to communicate the uncertainty associated with these model predictions. However, the majority of work on uncertainty has focused on traditional probabilistic …

A Benchmark for Interpretability Methods in Deep Neural Networks

2018 · arXiv (Cornell University)

We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods produce estimates of feature …