Scientific Machine Learning (SciML) = Scientific Computing + Machine Learning. Machine Learning and deep learning techniques have emerged to revolutionize conventional methods of scientific computing and discovery (such as modeling, solving differential equations, parameter estimation, equation discovery, etc.), crafting a new generation of machine learning methods for complex applications across science and engineering. This course will introduce this newly emerged paradigm and research trend, including topics of physics-informed neural networks (PINN), neural operators, governing equation discovery, and differentiable physics, etc. The course is designed as a project-oriented one, bridging practice and theory, aiming for real-world problems. At the end of the course, students are expected to understand the principles and methods of SciML, and to have hands-on implementations with Python.
Unlock more information by signing in with your HKUST account.