K
Klaus-Robert Müller
Researcher at Technical University of Berlin
Publications - 799
Citations - 98394
Klaus-Robert Müller is an academic researcher from Technical University of Berlin. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 129, co-authored 764 publications receiving 79391 citations. Previous affiliations of Klaus-Robert Müller include Korea University & University of Tokyo.
Papers
More filters
Proceedings Article
Explainable Deep One-Class Classification
Philipp Liznerski,Lukas Ruff,Robert A. Vandermeulen,Billy Joe Franks,Marius Kloft,Klaus-Robert Müller +5 more
TL;DR: Fully Convolutional Data Description (FCDD) as discussed by the authors is an explainable deep one-class classification method, where the mapped samples are themselves also an explanation heatmap, and provides reasonable explanations on common anomaly detection benchmarks with CIFAR-10 and ImageNet.
Proceedings ArticleDOI
Revealing the neural response to imperceptible peripheral flicker with machine learning
Anne K. Porbadnigk,Simon Scholler,Benjamin Blankertz,Arnd Ritz,Matthias Born,Robert Peter Scholl,Klaus-Robert Müller,Gabriel Curio,Matthias S. Treder +8 more
TL;DR: Common Spatial Pattern filtering in combination with classification based on Linear Discriminant Analysis could be used to reveal the effect for additional participants and stimuli, with high statistical significance, to show the benefit of machine learning techniques for investigating this effect of subconscious processing.
Book ChapterDOI
Robust Ensemble Learning for Data Mining
Gunnar Rätsch,Bernhard Schölkopf,Alexander J. Smola,Sebastian Mika,Takashi Onoda,Klaus-Robert Müller +5 more
TL;DR: A new boosting algorithm which similarly to v- Support-Vector Classification allows for the possibility of a pre-specified fraction v of points to lie in the margin area or even on the wrong side of the decision boundary is proposed.
Book ChapterDOI
Deep Transfer Learning for Whole-Brain FMRI Analyses
TL;DR: In this paper, transfer learning was applied to the decoding of cognitive states from whole-brain functional Magnetic Resonance Imaging (fMRI) data in clinical settings, where patient data are scarce.