Since completing my Ph.D. in 2019 in Computer Science at Harvard, I have been working in the Department of Epidemiology to bring deep learning research to the Harvard medical community, and the medical field, more broadly. Toward this end, I have developed a series of new approaches for understanding, analyzing, and updating neural networks and their associated datasets.
My current research direction is summarized at a high-level here: From Parameter Identification to Introspection, Constrained Inference, & Updatability: Toward An Actionable Understanding of Neural Networks.
For the more visually inclined, I have uploaded some recent presentation materials that provide an overview of this line of work, and the images included at the bottom of this page (or here as a single PDF) summarize the key aspects.
As a fun aside, I am the creator of reorder.coffee, an educational game for advanced language learners.
Uncertainty is but a distance to what is known...
