Speaker: Youngjoon Hong (San Diego State University)
When: 2020, July 24, 10:00--12:00.
Where: Building 108, Room 319.

Titie: Deep learning algorithm with the aid of numerical methods

Abstract: Deep learning is a process by which machines learn to perform tasks based upon data. The exponential growth of machine learning models and the extreme success of deep learning have seen application across a multitude of disciplines. In this talk, a background of the neural network is described, and data-driven numerical methods are introduced. In many physical systems, the governing equations are known with high confidence, but direct numerical solution is prohibitively expensive. Often this situation is alleviated by writing effective equations to approximate dynamics below the grid scale. This process is often impossible to perform analytically and is often ad hoc. In this regard, we propose data-driven numerical approaches, a method that uses machine learning to systematically derive discretizations for continuous physical systems.