Speaker：Hailiang Liu (Iowa State University)

Time：2023-5-29, 9:30

Location：Conference Room 106 at Experiment Building at Haiyun Campus

Abstract:

We will present a partial differential equation framework for deep residual neural networks and for the associated learning problem. This is done by carrying out the continuum limits of neural networks with respect to width and depth. We study the well-posedness of the forward problem, and establish several optimal conditions for the inverse deep learning problem. This talk concerns several mathematical aspects of deep learning and the use of optimal control tools in solving the learning problem. This presentation is based on a joint work with Peter Markowich (KAUST).