About

Hello! I’m a PhD candidate in Computing and Data Science at Boston University. My area of focus is within interpretability for machine learning and AI systems. Currently, I’m most interested in how techniques from this area can be used to develop safe methods for advancing scientific problems. Lately I have been been working on a project which applies mechanistic interpretability techniques to reliably extract and organize data from coastal ecosystems literature. Previously I have worked on algorithms for interpretable clustering models, and prior to that I was studying spatio-temporal patterns of spread in Covid-19.