Looking for technical training for your team? Get in touch so we can help.

Fooling Neural Networks; more

January 8, 19:00

Berlin, Germany
betahaus - innospace, Prinzessinnenstrasse 19-20 10969, Berlin

External Registration

Open Registration Page

Talk 1: Katharina Rasch - Fooling neural networks
Abstract: It is surprisingly easy to fool deep neural networks (and other machine learning models). Change a few pixels in an image (changes not visible to humans!) and suddenly a zebra is classified with high confidence as a microwave. Let's look at some methods for generating such adversarial examples and discuss what this could tell us about what our models are actually learning.
Here is a good read if you can't make it.

Berlin Machine learning group Berlin Machine learning group

Propose talk to Berlin Machine learning group