About

This school aimed at providing a pedagogical introduction of the methods of machine learning in modern materials science to young researchers, as well as established ones interested in rapidly adopting machine learning methods in their work. The discussed topics included:

• Machine Learning accelerated high-throughput searches based on density functional theory (and beyond) simulations
• Bayesian optimization of materials and molecular properties
• Generative models for materials and molecules design
• Large language models and embeddings for materials and molecules property prediction
• Automated construction of machine learning interatomic potentials
• Non-adiabatic and excited state dynamics with machine learning models
• Learning coarse-grained models
• Integrating experimental data in machine-learning-driven materials discovery

Resources

• The official school website
• Archive of the video streams of the lectures
• GitHub repository containing 10 hands-on exercises