Please see my Research Gate or Google Scholar for the full list!

We propose a framework to combine decision trees and neural networks, and show on image classification tasks that it enjoys the complementary benefits of the two approaches, while addressing the limitations of prior work.
Preprint: accepted at ICML, 2019.

Preprint: accepted at CVPR, 2019.

In MICCAI, 2018.

In MICCAI, 2018.

In MICCAI, Spotlight (top ~5%), 2018.

In ICML, Long Oral, 2018.

In MICCAI, Oral (top ~4%) and winner of Young Scientist Award, 2017.

In NeuroImage, 2017.

We propose a Bayesian variant of random forests, which provides an estimate of uncertainty over prediction which can be used to assess its accuracy in the absence of ground truth. We have shown that the predictive uncertainly correlates well with the accuracy and can highlight abnormality not represented in the training data.
In MICCAI, 2016.

Recent & Upcoming Talks