Academics

Solving Partial Differential Equations with Data Driven Machine Learning Methods

Time:2023-03-02 ~ 2023-06-15 Thu 09:50 - 12:15

Venue:ZOOM: 559 700 6085 PW: BIMSA

Speaker:Xiaoming Zhang

Prerequisite

Basic knowledge on numerical methods for partial differential equations and machine learning methods


Abstract

This course reviews the publications of the recent years on using machine learning methods to solve partial differential equations, such as Physics Informed Neural Network (PINN). The course will cover the materials on forward method, inverse method, reduced order modeling, and the assimilation of observational data to the scientific principles.


Lecturer Intro.

Dr. Zhang Xiaoming received his bachelor's, master's, and doctor's degrees from Zhejiang University, Peking University, and Massachusetts Institute of Technology. He is currently a research fellow at the Beijing Institute of Mathematical Sciences and Applications, responsible for the artificial intelligence and big data research team. Dr. Zhang has long been engaged in the research, development, and application of artificial intelligence technologies to big data prediction and resource optimization and allocations problems. He presided over the development of digital intelligence service platform "printing and dyeing brain", which was well recognized in the industry. At present, his work focuses on the research and development of digital twins and process twins in the industrial field.

DATEMarch 2, 2023
SHARE
Related News
    • 0

      Introduction to hyperbolic partial differential equations and conservation laws

      PrerequisiteMulti-variable Calculus, Basic Partial Differential Equation, Basics of Riemannian Geometry(optional)AbstractThe course introduces hyperbolic partial differential equations and conservation laws from both historical and modern perspectives, focusing on important examples rather than general theory. The classical concepts such as characteristics and Riemann invariant plays an indispe...

    • 1

      Physics-informed neural networks for solving differential equations

      PrerequisiteKnowledges on mathematical physics equations, deep neural networks and the Python language.AbstractDifferential equations can describe various natural and social phenomena. The physics-informed neural networks (PINNs), as a deep learning framework, is a powerful and effective way in solving forward and inverse problems involving differential equations. The course will review the pub...