Prof. Ullrich Köthe

ZOOM Meeting

July 8th, 2021

2 pm

Chair: Prof. Matthias Rarey

Invertible Neural Networks and their Applications in the Sciences

Invertible neural networks (INNs) are designed to run efficiently in both the forward (from inputs to outputs) and backward direction (from outputs to inputs). This unique capability opens up many interesting opportunities for uncertainty quantification, concept disentanglement and interpretability, and the efficient Bayesian treatment of inverse problems. The talk will introduce the basic concepts behind INNs and highlights applications in image analysis and epidemiological modelling.

Please subscribe here for news and Zoom links regarding our colloquia or contact dashh-office@desy.de for the individual Zoom link of an online event!