Program
Machine Learning for Material Science (a biased introduction)
- achieving the accuracy of quantum mechanics, without the electrons
- kernel ridge regression and Gaussian processes
- artificial neural networks with predefined descriptors
- message passing neural networks with learnable descriptors
- more data or more physics ?
- challenges: uncertainty prediction, active learning, data efficiency, delta-learning,...
full schedule:
Thursday 26/03/2026 rm 131 9-11 AM
Thursday 02/04/2026 rm 131 9-11 AM
Friday 10/04/2026 rm 131 9-11 AM
Friday 17/04/2026 rm 131 9-11 AM
Friday 24/04/2026 rm 131 9-11 AM
Monday 04/05/2026 rm 131 9-11 AM
Friday 08/05/2026 rm 131 9-11 AM