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
Posted Content
Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctions
Kristof T. Schütt,Michael Gastegger,Alexandre Tkatchenko,Klaus-Robert Müller,Reinhard J. Maurer +4 more
TL;DR: In this paper, a deep learning framework for the prediction of the quantum mechanical wavefunction in a local basis of atomic orbitals from which all other ground-state properties can be derived.
Posted ContentDOI
DeepCOMBI: Explainable artificial intelligence for the analysis and discovery in genome-wide association studies
Bettina Mieth,Alexandre Rozier,Juan Antonio Rodríguez,Marina M.-C. Höhne,Nico Görnitz,Klaus-Robert Müller,Klaus-Robert Müller,Klaus-Robert Müller +7 more
TL;DR: The performance of DeepCOMBI in terms of power and precision is investigated on generated datasets and a 2007 WTCCC study and it is shown to outperform ordinary raw p-value thresholding as well as other baseline methods.
Journal ArticleDOI
On robust parameter estimation in brain–computer interfacing
Wojciech Samek,Shinichi Nakajima,Motoaki Kawanabe,Klaus-Robert Müller,Klaus-Robert Müller,Klaus-Robert Müller +5 more
TL;DR: The results show that state-of-the-art BCI algorithms benefit from robustly estimated parameters, and a novel hierarchical view on robustness is introduced which naturally comprises different types of outlierness occurring in structured data.
Posted ContentDOI
Unification of Sparse Bayesian Learning Algorithms for Electromagnetic Brain Imaging with the Majorization Minimization Framework
Ali Hashemi,Ali Hashemi,Chang Cai,Gitta Kutyniok,Gitta Kutyniok,Klaus-Robert Müller,Srikantan S. Nagarajan,Stefan Haufe +7 more
TL;DR: This paper proposes a novel method called LowSNR-BSI that achieves favorable source reconstruction performance in low signal-to-noise-ratio settings and shows neurophysiologically plausible source reconstructions on averaged auditory evoked potential data.
Proceedings Article
v-Arc: Ensemble Learning in the Presence of Outliers
Gunnar Rätsch,Bernhard Schölkopf,Alexander J. Smola,Klaus-Robert Müller,Takashi Onoda,Sebastian Mika +5 more
TL;DR: A new boosting algorithm is proposed which allows for the possibility of a pre-specified fraction of points to lie in the margin area, even on the wrong side of the decision boundary.