The Texas A&M Institute of Data Science (TAMIDS) invites you to attend the 2022 TAMIDS Data Science Webinar series on Mar 22nd, 2022. This webinar series will introduce some intermediate and advanced topics of Data Science to Texas A&M students and researchers.
Presenter:
Dr. Ming Zhong is a postdoctoral researcher in the Scientific Machine Learning Lab (SciML Lab) at the Texas A&M Institute of Data Science (TAMIDS). He works with Prof. Ulisses Braga-Neto on various physics-informed machine learning methods for solving stiff and hyperbolic PDEs. Ming received his Ph.D. in Applied Mathematics, under the guidance of Dr. Eitan Tadmor from the Department of Mathematics at the University of Maryland.
Research Interests:
- Physics-Informed Machine Learning of Collective Behaviors from Observation
- Physics-Informed Machine Learning for solving various PDEs
- Numerical PDEs, especially central schemes for hyperbolic conservation laws
- Computational Optimal Transport Plan
- Geometric Numerical Integrators
- Scientific Computing (MPI, openMP, CUDA)
Time:
2:00 PM – 3:30 PM CDT, Mar 22nd
Description:
Traditional numerical solutions of PDEs require extensive preparation of meshing and proper choice of derivatives, numerical fluxes, interpolation schemes, etc. We propose two new machine learning-based methods, namely Gaussian Processes and Deep Neural Networks, as resourceful additions to the family of well-established numerical methods for solving PDEs to avoid some of the hassles of using traditional methods. We discuss the implementation of both methods for various nonlinear PDEs and the advantages/disadvantages of both. Implementation will be in Python (with Tensorflow 2.0).
Prerequisites:
Basic knowledge of Python, linear algebra, and calculus is assumed.