Ullrich Köthe | Analyzing Inverse Problems in Natural Science using Invertible Neural Networks

Watch Ullrich Köthe's talk during the First French-German Meeting in Physics, Mathematics and Artificial Intelligence Theory that took place from November 4 to 6, 2019 in Paris.
Abstract:
Uncertainty quantification is a hot topic in neural network research. This talk will focus on inverse problems, where high uncertainty arises from the inherent ambiguities of ill-posed inverse processes. This type of problem is ubiquitous in natural sciences, and existing approaches are either very expensive or suffer from drastic approximations. The talk presents a new class of invertible neural networks that generalize established Bayesian approaches from the linear to the non-linear setting.
These networks work equally well in the forward as well as the inverse direction and thus enable new training and approximation methods, which become asymptotically exact in the perfect convergence limit. A variety of promising results from medical imaging, computer vision, and environmental physics demonstrate the practical utility of the new method.
_____
Follow us on:
LinkedIn: https://www.linkedin.com/company/cealist
Twitter: https://twitter.com/CEA_List
Website: http://www-list.cea.fr/en

Видео Ullrich Köthe | Analyzing Inverse Problems in Natural Science using Invertible Neural Networks канала CEA-List