Computational and Mathematical Global Health Group
We do traditional epidemiology to answer policy relevant questions as well as explore new methodologies from statistics and deep learning that can improve prediction and estimation.
We employ contrastive learning to study images in both satellites and medical cases. We also are in the beginning of utilizing deep learning for protein structure similarity.
We study renewal, hawkes and branching processes to model infectious disease data. Our focus here has recently been on mathematical foundations, but we also do applied work on economics and health.
We are studying the question of how to explore the vastness of tree space and developing approximate methods for whole genome analysis
We are building the mathematical foundations to estimate time 0
