Data-Driven Modeling in Science and Engineering / Spring 2025
Updates
- New Lecture is up: Modal Decomposition in Spatio-Temporal Systems
- New Lecture is up: Unsupservised Learning
- New Assignment released: [Problem Set #4 - Data-Driven Reduced Order Modeling]
- New Lecture is up: Residual Minimization & Physics Informed Neural Networks
- New Lecture is up: Symbolic Identification of Differential Equations from Data
- New Lecture is up: Modeling the World with Differential Equations
- New Lecture is up: Time Series Analysis
Course Description
How do we go from a high dimensional, noisy, nonlinear, complex, and multiscale universe to simple and predictive mathematical models? This course introduces modern machine learning techniques using a wide variety of examples in physical, social and biological sciences. Modern data-driven approaches that take advantage of recent advances in machine learning are introduced, including: sparse identification of differential equations, dynamics mode decomposition, and physics informed neural networks.