Vladimir Nikolić and Leander Schröder testimonial

For us there were two main reasons why the seminar was so good. First of all, you meet people who are interested in the same thing as you are and who are willing to help out any way they can, no matter if they are part of the teaching group or your peer participant. The second thing is – the lectures are actually good. There’s a lot of content to go through and always something to discuss, but don’t fret, it all starts from the very basics of ML. So, even if you don’t have any idea about anything, the seminar will pick you up at whatever skill level you’re at.

Moreover, you get to work on a project of your choice. In our case, we decided to do something useful and made a neural net to recognize night sky clouds for the local meteor observing group. The solution is more than basic image processing, as night sky clouds aren’t as visible as the ones during the day. The low altitude ones are sometimes visible, but otherwise the lack of stars is a hint of a cloud presence. This requires careful labeling of clouds in images for the network to learn from. The project extended beyond the seminar and actually won a prize at a conference later on.

You can find the code online at GitHub.

Also, there’s another reason - the coffee is super cheap and the landscape is stunning.

Cheers,
Vladimir & Leander