Deep learning-based numerical algorithms for solving partial differential equations
Project Description
Use deep learning-based numerical algorithms to solve partial differential equations that arise from science and engineering.
Supervisor
XIANG Yang
Quota
3
Course type
UROP1100
UROP2100
UROP3100
UROP4100
Applicant's Roles
Strong Mathematics background; familiar with programming; knowledge of numerical methods. Prerequisites: multivariable calculus (MATH 2011/MATH 2023/MATH 3043), linear algebra (MATH 2111/MATH 2121/MATH 2131/MATH 2350), differential equations (MATH 2350/MATH 2351/MATH 2352), numerical analysis (MATH 3312)
Applicant's Learning Objectives
(i) Understand the algorithms of deep learning-based numerical algorithms to solve partial differential equations. (ii) Able to apply the deep learning methods to solve problems in science and engineering.
Complexity of the project
Challenging