Machine learning and artificial intelligence play an increasingly critical role in modern science. This lecture series will provide an introductory tutorial on these methods for researchers interested in a range of physical problems, and will give participants a basic understanding of the principles of current physics-informed machine learning approaches and introduce several widely-used techniques. Topics will include model reduction, deep learning approaches to differential equations, graphical model tools, and optimization methods.
|December 14, 2020||Application Agnostic Learning from Data: Questions, Formulations, Approaches|
|December 15, 2020||Setting Up Physics (Science) Informed (Explainable) Learning: Questions, Formulations|
|December 16, 2020||Physics Informed Model Reduction (e.g. testing, resolving or excluding models/theories)|
|January 5, 2021||Graphical Model Tools (i.e. formulations, methods, algorithms) for Inference, Learning, and Optimization (will allow to account most naturally physics constraints, relations, dependencies, etc)|
|January 6, 2021||Attempt of Synthesis|