Abstract for Research Seminar
Recent advances in deep learning are beginning to transform how we model and understand infectious disease dynamics. By integrating flexible function approximation with mechanistic epidemic models, these approaches offer new opportunities to capture complex transmission patterns, incorporate diverse data sources, and improve forecasting and inference. In this talk, I will provide an overview of the evolving landscape of deep learning methods for epidemic modeling, highlighting key opportunities and challenges at the intersection of machine learning and infectious disease epidemiology. I will also discuss several recent and ongoing projects from my research group that illustrate how these frameworks can be applied to real-world epidemic data.
About the Speaker
Max Lau is an Associate Professor at Emory University, where he works at the intersection of statistics, epidemiology, and computer science. As a home-grown HKU graduate, he began his academic journey by studying Statistics as an undergraduate at HKU, followed by an MPhil in the School of Public Health at HKU. He then went on to pursue a PhD in Statistics in Edinburgh, followed by postdoctoral training in Princeton. After that, he spent two years working in the pharmaceutical industry, before returning to academia and joining Emory University as an Assistant Professor in the Department of Biostatistics and Bioinformatics. Raised from a humble background, Max's journey to success had never been smooth and rosy. He didn't give up, believing his breakthrough will come and his determination eventually paid off.