This page contains topic areas for the students. The information contained at this page is preliminary and may still change. We will later add detailed description of the topics. The list of topics is structured based on methods instead of, e.g., various sciences, because each of the methods can be applied to several domains. We give will give pointers to how the methods have been used in various sciences later in the detailed project descriptions. The students can also propose the topics of their own.

  1. Data wrangling (preprocessing)
  2. Data engineering (from raw data to analysable data)
  3. Interactive data exploration
  4. Data visualization and dimensionality reduction methods
  5. Classification methods in natural sciences, with examples
  6. Regression methods in natural sciences, with examples
  7. A peek into black box (explaining how supervised learning methods work)
  8. Statisticial significance and robustness of results in data analysis
  9. How to use simulations to find proper simulation parameters
  10. How to do fast simulations with deep learning
  11. Tools: programming languages
  12. Tools: AI libraries
  13. Tools: Visualisation

A more detailed (still tentative) list of topics is also available.