Hacking Deep Learning (Bar Ilan) Workshop Videos now online. Thanks for my friend Prof. Yossi Keshet for organizing and inviting me!
One notable talk which is unfortunately missing from the videos is of Prof. Adi Shamir described in this paper. The work analysis how many pixels one should change to confuse a deep learning based classifier. The result is surprising - only a few! A related describe work is this.
No comments:
Post a Comment