I am a 5th-year Ph.D. student in Aerospace Engineering at the University of Texas at Austin since January 2021. I obtained his Bachelor’s and Master’s degree in Civil Engineering from Ho Chi Minh city University of Technology, after which I worked as a graduate research assistant and teaching assistant at the same university.
My current interests are in the broad areas of machine learning, numerical analysis, and scientific computing. I have developed the model-constrained deep learning approaches for accelerating both numerical simulations and inverse problems. At the heart of the model-constrained learning approaches is the combination of data randomization and differentiable physics model, leading to a low demand on training data, good generalization, long term prediction stability, and more. Additionally, I also worked on designing transformer architecture, diffusion models, and foundation models.
Beyond machine learning, I proposed a data-informed active subspace framework and unified randomized algorithm for solving inverse problems.
Double Mach Reflection Animation
I love coding and sharing useful tutorials. I recorded some useful tricks and tips for my Ph.D. journey in this Github repo. My favorite machine learning platform is JAX which allows my to work flexibly with machine learning, differentiable PDEs solver, and computation parallelism.
Research interests
- Scientific Machine Learning
- Model-Constrained Machine Learning
- Differentiable Numerical Simulations
- Inverse Problems
- Partial Differential Equations