October 23, 2017, LINK-SIC arranged the Core Competence Workshop "Learning from a Control perspective".

9.00 – 9.15: Welcome

9.15 – 10.00: Michael Felsberg, LiU. Deep visual features: Selection, fusion, and compression with applications in visual object tracking. (Download presentation)

10.00 – 10.15: Coffee

10.15 – 11.00: Lennart Ljung, LiU. The historic roots of learning in control: Stochastic approximation and recursive identification. (Download presentation)

11.15-12.00: Håkan Hjalmarsson, KTH. Iterative feedback tuning (IFT) in a learning perspective. (Download presentation)

12.00 – 13.15: Lunch

13.15-14.00: Torkel Glad, LiU. Reinforcement learning from an optimization viewpoint. (Download presentation)

14.15-15.00: Mikael Norrlöf, ABB/LiU: Learning for improved control performance in industrial robot applications. (Download presentation)

15.00-15.15: Coffee

15.15-16.00: Lennart Ljung, LiU: Influences from machine learning in today's System Identification. (Download presentation)

16.15-17.00: Thomas Schön, Uppsala University. Constructing probabilistic Newton-type algorithms to learn nonlinear dynamics. (Download presentation)