Senior Research Scientist Joel LeBlanc of Michigan Tech Research Institute (MTRI) will present his lecture, “Testing the Validity of Physical (Software) Models in Inverse Problems,” on Friday, December 4, 2020, at 3:00 p.m. via online meeting.
The lecture is presented by the Michigan Tech Department of Computer Science.
LeBlanc has a Ph.D. in Statistical Signal Processing. His areas of expertise include statistical signal processing, applied nonconvex optimization, EO/IR imaging, and Synthetic Aperture Radar (SAR) imaging. His research interests are in information theoretic approaches to inverse-imaging, computational techniques for solving large inverse problems, and fundamental limits of sensing.
Numerical simulations are the modern analog of the “physical system” referenced by Rosenblueth and Wiener in their 1945 paper “The Role of Models in Science.” This talk will introduce the inverse-problem approach for making inferences about the physical world and discuss how the Maximum Likelihood (ML) principle leads to both performant estimators and algorithm agnostic bounds on performance. The resulting estimators and associated bounds are only valid when global convergence is achieved, so I will present new results on global convergence testing that I believe are widely applicable. Finally, I will discuss some of my ongoing research interests: optimal resource allocation and testing for adversarial behavior through model relaxation.
Michigan Tech Research Institute focuses on technology development and research to sense and understand natural and human-made environments. Through innovation, education, and collaboration, the Institute supports meaningful solutions to critical global issues, from infrastructure to invasive species, national security to public health.