Skip to Main Content

Applied Math Seminar: Selection Dynamics for Deep Neural Networks by Professor Hailiang Liu

This is a past event.

Friday, February 18 at 4:00pm to 5:00pm

Virtual Event

Please join us remotely for a seminar by Hailiang Liu from Iowa State University

In this talk, Liu shall 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, the large time solution behavior, and the characterization of the steady states of the forward problem. Several useful time-uniform estimates and stability/instability conditions are presented. We state and prove optimality conditions for the inverse deep learning problem, using standard variational calculus, the Hamilton-Jacobi-Bellmann equation and the Pontryagin maximum principle. This serves to establish a mathematical foundation for investigating the algorithmic and theoretical connections between neural networks, PDE theory, variational analysis, optimal control, and deep learning. This presentation is based on a recent joint work with Peter Markowich (KAUST).

Hosted by Hakima Bessaih

Dial-In Information

Join Zoom Meeting

Meeting ID: 930 5388 4755
Passcode: AAM2022

Event Type

Academics, Lectures & conferences


Students, Faculty & Staff



Department of Mathematics and Statistics
Add to Calendar
Google Calendar iCal Outlook

Recent Activity