8 July 2021
Colloquium by Prof. Ullrich Köthe, Visual Learning Lab, University of Heidelberg
Thursday, 8 July 2021 14:00, Zoom Meeting
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, andt he 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 contact DASHH office for the Zoom access information, see link below.
Further information concerning the speakers and the lectures can also be found here: