1 citations · 1 across the 2 of their papers we have counts for
3 papers
cs.CV2021★ 1 cited
Bounded logit attention: Learning to explain image classifiers
Thomas Baumhauer, Djordje Slijepcevic, Matthias Zeppelzauer
Explainable artificial intelligence is the attempt to elucidate the workings of systems too complex to be directly accessible to human cognition through suitable side-information r…
cs.LG2020
Machine Unlearning: Linear Filtration for Logit-based Classifiers
Thomas Baumhauer, Pascal Schöttle, Matthias Zeppelzauer
Recently enacted legislation grants individuals certain rights to decide in what fashion their personal data may be used, and in particular a "right to be forgotten". This poses a…
math.LO2019
Higher random indestructibility of MAD families
Thomas Baumhauer
We give a combinatorial characterization of when a maximal almost disjoint family of a weakly compact cardinal is indestructible by the higher random forcing . We…