The growth of data from simulations and experiments is expanding beyond a level that is addressable by established scientific methods. The so-called “4V challenge” of Big Data –Volume (the amount of data), Variety (the heterogeneity of form and meaning of data), Velocity (the rate at which data may change or new data arrive), and Veracity(uncertainty of quality) – is clearly becoming eminent also in the sciences. Controlling our data, in turn, sets the stage for explorations and discoveries. Novel approaches and tools of Artificial Intelligence (AI) can find patterns and correlations in data that cannot be obtained from individual calculations or experiments and not even from high-throughput studies.
This course provides the basis for understanding and contributing to the novel field of data-driven approaches in materials science. It will cover an introduction to AI and most popular machine-learning methods, FAIR (Findable, Accessable, Interoperable, Resuseable) data infrastructures, and more. Lectures will be complemented with hands-on exercises.
- Kursverantwortliche/r: Claudia Draxl
- Kursverantwortliche/r: Martin Kuban
- Kursverantwortliche/r: Santiago Rigamonti