https://www.math.emory.edu/~lruthot/
Thu, April 18, 2024, 9:00-10:00 am PST via Zoom
Title: Differential Equations for Continuous-Time Deep Learning.
Abstract: In this talk, we introduce and survey continuous-time deep learning approaches based on neural ordinary differential equations (neural ODEs) arising in supervised learning, generative modeling, and numerical solution of high-dimensional optimal control problems. We will highlight the theoretical advantages and numerical benefits of neural ODEs in deep learning and their use to solve otherwise intractable problems in optimal control and Bayesian inversion.