May 6, 2014: The project presentations starts at 15.15 tomorrow.
Apr 9, 2014: The exams can be collected from the administrators of the IT department.
ar 27, 2014: There are many interesting projects in this years edition of the course, have a look at this page for the teams and project titles.
Mar 21, 2014: The project proposals will be presented on Monday in ITC 4306 starting at 13.15. All are welcome!
Mar 6, 2014: Here is the link to the information about how to generate nice looking animations of Gaussian Processes (thank’s to Andreas). Click here for a nice GP presentation making use of this.
Mar 4, 2014: During the lecture today I mentioned sparse GPs, if you are interested have a look at this overview or this more detailed explanation. There is also a recent overview on the use of kernels in system identification available here.
Feb. 13, 2014: In order to make room for the IT PhD student ski trip, we decided to move the lectures scheduled for March 18 and March 20. The new dates are March 21 and April 3 (we added another lecture at the end of the course). The updated schedule is available here and it you have subscribed your devices should already be updated.
Feb. 12, 2014: During the lecture yesterday we spoke briefly about l_p-regularized least squares. We mainly talked about the convex problems arising from p=1 and p=2, but there was also a very good question concerning the possible use of for example the l_0 norm. Here it is important to note that p=1 is a convex problem, p<1 leads to nonconvex problems. An obvious strategy is to start with norm p=1 and then initialize the nonconvex problem for the p<1 norm in the solution of the p=1 norm. Click here for some results clearly indicating that it can be interesting to consider l_p norms with p<1.
Feb. 11, 2014: During today’s lecture we had a look at a bias-variance trade-off example from Henrik Ohlsson’s PhD thesis (Example 2.3 on page 24), you can download the thesis here.
Feb. 4, 2014: Check out this nice introduction to statistical machine learning (geared towards non-mathematical sciences) Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning - with Applications in R, Springer, 2013.
Jan. 10, 2014: The schedule is available here.
Oct. 2, 2013: The 2014 home page is now available. The course will start in early February 2014, but the exact dates are still to be decided.