Welcome to the 2017 summer school on graphical models. This will be the ninth in a series of summer school organized together with the Image Analysis and Computer Graphics section at DTU. The concept is to invite 2-4 internationally renowned experts to teach a week-long course together with local teachers from KU and DTU. The participants are a good mix of students from KU and DTU and international participants. The summer schools are held in remote locations to encourage interaction between students and teachers. In addition to bringing international expertise in to the groups, the summer schools also provide an important networking opportunity for the students.

Important dates

  • —-: Registration is binding
  • July 1.: Registration deadline
  • —-: Poster submission deadline
  • August 14.-18.: Summer school

Scientific content

The summer school will consist of 5 days of lectures and exercises. The students will be expected to read a predefined set of scientific articles on graphical models prior to the course. Additionally, the students should bring a poster presenting their research field (preferably with an angle towards machine learning in image analysis).

The course will consist of the following parts:

  • A crash course on the basics of graphical models.
  • A theoretical insight in the challenges of graphical models.
  • A practical session with hands-on exercises.
  • Applications of graphical models in image analysis.

Learning outcomes

After participating in the summer school, the student should

  • Understand graphical models and be able to differentiate between the different types of models.
  • Have a strong knowledge about the theoretical foundations of graphical models learning
  • Be able to implement basic graphical models from scratch and apply using appropriate model reduction techniques.
  • Be able to apply graphical models for his/her own research projects.

Link to previous summer schools