Doctorat, Formation, Recherche
24.09.20 DATAIA Seminar | « Solving inverse problems with invertible neural networks » - Ulrich Köthe
… backwards from observations to the hidden characteristics of a system. I will focus on three aspects of interpretability: reliable uncertainty quantification, … and inverse direction -- are great tools for that kind of analysis: They act as non-linear generalizations of …Article publié le: lun 21/09/2020 - 23:05