17.03.2022Inaugural lecture by Manuel Günther, 21.03.2022

You are warmly invited to the inaugural lecture of Prof. Dr. Manuel Günther:

How Algorithms Know that they Don't Know - Open-Set in Classification and Face Recognition

In the idealized academic world, algorithms are only presented with data that they know how to handle. In the real world, however, algorithms are confronted with unknown objects, and many times the algorithms fail to recognize that and just incorrectly treat the objects as something known, and often they do that with high confidence. Prof. Manuel Günther investigates methods that allow modern deep learning techniques to detect these unknown objects as something they should not handle at all, and he shows how these methods help in protecting innocent pedestrians from being treated as criminals.

Manuel Günther received his Master and PhD degrees in computer science and engineering from the Technical University of Ilmenau (Germany), while actually doing his doctorate at the Ruhr-University of Bochum (Germany). Afterward, he worked as a postdoc at the Idiap Research Institute in Martigny (Switzerland), as a Research Associate at the University of Colorado Colorado Springs (USA), and as a research engineer at TrinamiX in Ludwigshafen (Germany). Since July 2020, Manuel Günther is a DSI Assistant Professor at the Department of Informatics of the University of Zurich, where he is engaged in teaching Deep Learning to Master and PhD students, and in research on open-set classification, face recognition, and deep learning. 

The inaugural lecture is public and will take place in the Aula of the University of Zurich (KOL G-201, Rämistrasse 71, 8006 Zurich) on Monday, March 21, 2022, at 6.15pm. No reservation is needed.

A live stream is available for people who cannot attend the event in person: https://vimeo.com/event/810511

We are looking forward to seeing you there!