Date and time: 19-30 June 08:00-18:00 CEST – times might vary depending on the day
Course lecturer: G. Em Karniadakis, K. Shukla from Brown University
Title: PhD Summer School on Physics-Informed Neural Networks and Applications
Where: Digital Futures hub, Osquars Backe 5, floor 2 at KTH main campus AND F2
Directions: https://www.digitalfutures.kth.se/contact/how-to-get-here/
REGISTRATION is closed!
Information can be found on the website: https://pinns.se/pinn-summer-school-at-kth
The course syllabus is adapted for participants from engineering disciplines. It is focused on providing practical guidance toward the application of Physics-Informed Neural Networks and Deep Learning to problems in engineering research disciplines.
The course consists of a theoretical part and a project part. Participants from a broad range of disciplines are invited to learn how PINNs can be applied to their research subjects.
The course syllabus will cover a variety of topics:
- Introduction to Deep Learning Networks
- Neural Network
- TensorFlow, PyTorch, JAX
- Discovery of differential equations
- Physics-Informed Neural Networks (advanced)
- DeepONet
- {DeepXDE} or {MODULUS}
- Uncertainty quantification
- Multi-GPU machine learning
For questions, please contact Kateryna Morozovska: kmor@kth.se or info@pinns.se
