scispace - formally typeset
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, +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, +5 more
- 30 Jun 2013 - 
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

Guido Nolte, +3 more
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

Franziska Horn, +1 more
- 06 Feb 2017 - 
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, +10 more
- 15 Aug 2019 - 
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.