Dr. Aaron King, a professor at the University of Michigan, will present the first IBEST/CMCI Seminar of the semester on Thursday, January 24 at 12:30 p.m. in LSS 277. Dr. King is interested in studying evolution and ecology at long temporal and spatial scales using stochastic approaches. He’s done work on disease modeling and method/model/software development. His seminar talk is titled, “Efficient Scientific Inference for Stochastic Dynamical Systems.” If you would like to meet with Dr. King while he is on campus, please contact Ben Ridenhour.
Abstract: Scientific questions regarding the mechanistic operation of biological systems are often naturally formulated using Markov processes, but confronting the resulting models with data can be challenging. In this talk, I describe the essence of the difficulty, highlighting both the technical issues and the importance of the “plug-and-play property”. I then describe some efficient inference approaches for partially observed Markov processes and illustrate these with examples. I conclude by sketching promising new developments and describing some open problems.