Manifold provides a powerful tool to model high dimensional data. PDEs on the manifold can help us to reveal the intrinsic structure of the manifold. In this talk, we will discuss the relation between PDEs and some machine learning problem. Several models and algorithms are proposed.

This presentation is part of Minisymposium “MS24 - Data-driven approaches in imaging science (3 parts)”
organized by: Jae Kyu Choi (Institute of Natural Sciences, Shanghai Jiao Tong University) , Chenglong Bao (Yau Mathematical Sciences Center, Tsinghua University) .

Authors:

Zuoqiang Shi (Tsinghua University)

Keywords:

deep learning, machine learning, manifold, partial differential equation models, point cloud