ML4MatSci School is designed to equip current and prospective PhD students with the essential knowledge and practical skills needed to apply machine learning techniques in the field of Materials Informatics.
Through a combination of lectures, hands-on sessions, and collaborative discussions, participants will gain a solid foundation for integrating data-driven approaches into their research.
Key Scientific Focus Areas
- Fundamentals of Machine Learning & Artificial Intelligence
Core concepts, workflows, and practical considerations
- Image Processing for Materials Characterization
From segmentation to feature extraction in microscopy and beyond
- Large Language Models (LLMs) & Their Emerging Applications
Using LLMs for scientific text mining, synthesis, and discovery
- Datasets, Data Quality & Evaluation Metrics
How to prepare, validate, and measure the impact of your data
- Bayesian Optimization & Active Learning
Smart experimentation and efficient exploration of design spaces
- Advanced Topics in AI-Driven Materials Science
Including:
- Generative models (e.g., for molecule or structure generation)
- Explainable AI (XAI)
- Multi-modal learning
- AI for materials discovery pipelines
More information on the ML4MatSci School like agenda and registration you find here.
