DATAIA Seminar | « Solving inverse problems with invertible neural networks » - Ullrich Köthe
Ullrich Köthe (Université de Heidelberg) is leading the DATAIA seminar of September on « Solving inverse problems with invertible neural networks ».
Interpretable models are a hot topic in neural network research. This talk will focus on inverse problems, where one wants to infer backwards from observations to the hidden characteristics of a system. I will focus on three aspects of interpretability: reliable uncertainty quantification, outlier detection, and disentanglement into meaningful features. It turns out that invertible neural networks -- networks that work equally well in the forward and inverse direction -- are great tools for that kind of analysis: They act as non-linear generalizations of classical methods like PCA and ICA. Examples from physics, medicine, and computer vision demonstrate the practical utility of the new method.
The webinar will take place on September 24th 2020 at 15.00 and it will be live broadcasted.
It is recommended to use Google Chrome, Firefox, or the BlueJeans app (https://www.bluejeans.com/downloads) to join the webinar.
Don't miss out any new announcement about a new DATAIA seminar!
Subscribe to the DATAIA seminars mailing-list by clicking here