Physics Informed Machine Learning: Recap and Summary

Recap and summarize the key concepts of Physics Informed Machine Learning in this 24-minute video lecture. Explore the five stages of machine learning and how physics can be integrated into each stage. Delve into various architectures, symmetries, digital twins, and applications in engineering. Gain insights into the importance of dynamical systems and controls benchmarks. Learn about future modules, curriculum frameworks, and the dual problems of PIML. Get a sneak peek into topics such as parsimonious models, PINNs, operator methods, and case studies. Enhance your understanding of the intersection between AI/ML and physics through this comprehensive overview.

Intro
Future Modules
Curriculum Framework
The Dual Problems of PIML
Data-Driven Science and Engineering
Sneak Peak of the Modules
Sneak Peak: Parsimonious Models
Sneak Peak: PINNs
Sneak Peak: Operator Methods
Sneak Peak: Symmetries
Sneak Peak: Digital Twins
Sneak Peak: Case Studies & Benchmarks
Outro