Latest information


Welcome to the 2014 summer school on deep learning. This is the sixth in a series of summer school organized jointly by KU and DTU. 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

  • April 23. : (internal) registration deadline (staff members DIKU/DTU).
  • August 11.: Poster submission deadline.
  • August 18.-22.: 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 deep learning methods prior to the course. Additionally, the students should bring a poster presenting their research field (preferably with an angle towards deep learning). The course will consist of the following parts:

  • A crash course on neural networks and their implementation.
  • A theoretical insight in the challenges of designing and training neural networks.
  • A practical session with hands-on exercises.
  • Applications of deep learning.
Learning outcomes

After participating in the summer school, the student should

  • Understand deep (multi-layered) neural networks and be able to differentiate between the different types of networks (perceptrons, autoencoders, convolutional nets, recurrent nets and restricted Boltzmann machines).
  • Have a strong knowledge about the back-propagation algorithm and the theory behind a successful training of deep neural networks.
  • Be able to implement basic neural networks from scratch and train them using appropriate initialization and optimization techniques.
  • Be able to apply deep learning for his/her own research projects.