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
Brain Interface Design for Asynchronous Control
Guido Dornhege,José del R. Millán,Thilo Hinterberger,Dennis J. McFarland,Klaus-Robert Müller +4 more
TL;DR: This report provides an introduction to asynchronous control, summarizes the results to date, and details some key issues that specifically relate to brain interface design for asynchronous control.
Journal ArticleDOI
Decoding Brain States during Auditory Perception by Supervising Unsupervised Learning
Anne K. Porbadnigk,Anne K. Porbadnigk,Nico Görnitz,Marius Kloft,Marius Kloft,Klaus-Robert Müller +5 more
TL;DR: A novel supervised-unsupervised learning scheme is proposed, which aims to differentiate true labels from random ones in a data-driven way, and shows that this approach provides a more crisp view of the brain states that experimenters are looking for, besides discovering additional brain states to which the classical analysis is blind.
Proceedings Article
Analyzing Coupled Brain Sources: Distinguishing True from Spurious Interaction
TL;DR: A new BSS technique is proposed that uses anti-symmetrized cross-correlation matrices and subsequent diagonalization and the resulting decomposition consists of the truly interacting brain sources and suppresses any spurious interaction stemming from volume conduction.
Posted ContentDOI
Predicting Pairwise Relations with Neural Similarity Encoders
TL;DR: This paper introduces a novel neural network architecture termed Similarity Encoder (SimEc), which is designed to simultaneously factorize a given target matrix while also learning the mapping to project the data points' feature vectors into a similarity preserving embedding space.
Journal ArticleDOI
Resolving challenges in deep learning-based analyses of histopathological images using explanation methods
Miriam Hägele,Philipp Seegerer,Sebastian Lapuschkin,Michael Bockmayr,Michael Bockmayr,Wojciech Samek,Frederick Klauschen,Klaus-Robert Müller,Klaus-Robert Müller,Klaus-Robert Müller,Alexander Binder +10 more
TL;DR: This work shows how heatmaps generated by explanation methods allow to resolve common challenges encountered in deep learning-based digital histopathology analyses, and advocate pixel-wise heatmaps, which offer a more precise and versatile diagnostic instrument.