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
Transferring Unsupervised Adaptive Classifiers Between Users of a Spatial Auditory Brain-Computer Interface
Pieter-Jan Kindermans,Benjamin Schrauwen,Benjamin Blankertz,Klaus-Robert Müller,Michael Tangermann +4 more
TL;DR: A thorough leave-one-user-out offline analysis and additional preliminary online results from a spatial auditory ERP spelling study on inter-subject transfer of an unsupervised adaptive classifier indicate that the transfer approach reduces the warm-up time by approx.
Journal ArticleDOI
Neuronal correlates of emotions in human-machine interaction
TL;DR: Multi-channel EEG is acquired in four subjects while they were interacting with computer applications that have been specifically designed in order to provoke – in alternating phases – neural, positive or negative emotions.
Proceedings ArticleDOI
Explainable Deep Learning for Analysing Brain Data
TL;DR: Recent directions where deep learning is used for analysing brain imaging data, both in the context of BCI and fMRI are discussed – summarizing steps taken by the BBCI team and co-workers.
Posted Content
Estimating Local Function Complexity via Mixture of Gaussian Processes
TL;DR: This paper proposes Spatially Adaptive Bandwidth Estimation in Regression (SABER), which employs the mixture of experts consisting of multinomial kernel logistic regression as a gate and Gaussian process regression models as experts as experts.
Journal ArticleDOI
Modeling of molecular atomization energies using machine learning
TL;DR: This scheme maps the problem of solving the molecular time-independent Schrodinger equation onto a non-linear statistical regression problem, and uses a diagonalized matrix representation of molecules based on the inter-nuclear Coulomb repulsion operator in conjunction with a Gaussian kernel.