Rohan Jha

I'm a recent graduate from Brown University, where I was advised by Prof. Ellie Pavlick. I studied computer science and math.

I'm interested in natural language processing and understanding neural networks. In particular, I'm working on: (1) when deep models learn simple, low-hanging heuristics, as opposed to generalizable rules and (2) whether feature hardness can predict those that are learned downstream. I'm also interested in theoretical computer science (especially theoretical deep learning) and climate science, climate change, and sustainability.

My email is <first>d<last><at>outlook<dot>com. I'm also on LinkedIn and GitHub.