You do not have permission to edit this page, for the following reasons:
Please read before you start to fill in the form!
Please enter a basic description for the planned Self-Organized Session. For more information about Self-Organized Sessions head to Self-Organized Sessions.
Add times where you like to run your activities here by just pressing "Add another…". You can add multiple times if you like to split your event over multiple timeslots. A Self-Organized Session should have at least one timeslot though ;)
Enter a full description of the event here. The field allows using the full mediawiki syntax for text formating.
Conventional computer algorithms are superior to the human intellect in many regards: for instance at multiplying large numbers or winning at chess by analyzing huge numbers of moves. But there are also many tasks which come naturally to us yet exceed the capabilities of algorithms by vast amounts: Rigid algorithms can't decipher human handwriting or drive cars.
The recent breakthroughs in artificial intelligence circumvent these barriers by employing quite a different approach: They use artificial neural networks, which are inspired by the partially-understood way the human brain works.
The unique feature of artificial neural nets is that they aren't rigid, but can <em>learn</em>. Human programmers specify their rough structure and supply training data, but don't write a single line of code governing their behavior.
<strong>In the spirit of a good Unix command-line tool, this talk aspires to explain one thing and explain it well: How do artificial neural nets accomplish the feat of learning?</strong>
We'll see that the answer is related to a mathematical breakthrough made at the end of the 17th century and discuss why deep learning only surged in the last few years, even though the basics of artificial neural nets were already understood in the 1980s. We'll also touch upon some of the biggest problems of neural nets, which emerge directly from the way neural nets learn.
The talk doesn't require any advanced knowledge of mathematics. It's intended as a warmup to [https://events.ccc.de/congress/2017/Fahrplan/events/8860.html Katharine's talk on deep learning blindspots]. If you're already familiar with [http://neuralnetworksanddeeplearning.com/ Michael Neelson's book], then don't expect to learn anything new and come to this talk only if you want to contribute interesting remarks.
''[https://rawgit.com/iblech/mathematik-der-vorhersagen/master/vortrag-34c3/slides.pdf Slides]'' (will be extended after the congress)
This is a minor edit
Watch this page