ML Workshop Physics-Informed Neural Networks
The Workshops on Machine Learning techniques is for beginners students, PhD candidates, academic staff from fields such as physics, applied mathematics, chemistry, or biology who have a basic understanding of Python and machine learning. During the workshops, the focus will be on Physics Informed Neural Networks (PINNs).
These workshops are organized by the Machine Learning Center of the University of Warsaw and EUROCC2, represented by ICM of the University of Warsaw.
The registration is open.
more information
THE REGISTRATION
The Workshop schedule
Day 1
11.05.2024 (Saturday) [10:00 – 13:30]
- 10:00-11:00 Introduction to PyTorch (Szymon Nowakowski)
- 11:00-11:15 break
- 11:15-13:30 Hands-on exercises: (Szymon Nowakowski)
- Writing and running Python in Colab
- Using PyTorch to create and train simple neural networks
Materials for Day 1 are available in this repository and solutions are available in this repository
Day 2
18.05.2024 (Saturday) [09:00 – 13:00]
- 09:00-09:45 Short Lecture (Marek Bukowicki)
- Introduction to Physics-Informed Neural Networks (PINNs)
- The physics-informed loss function
- 09:45-10:00 break
- 10:00-10:45 Hands-on exercise: Training a PINN to solve a simple ODE (mass-spring-damper) (Marek Bukowicki)
- 10:45-11:00 break
- 11:00-13:00 Hands-on exercise: Training a PINN for parameter identification in PDE (heat transfer) (Grzegorz Gruszczyński)
Materials for Day 2 are available in this repository
Important information:
- The workshop will be conducted in English.
- The Workshops of Machine Learning will be taken remotely [on-line platform].
- The number of places is no limited.
- The registration is open.