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
Journal ArticleDOI
A mathematical model for the two-learners problem.
Jan Saputra Müller,Carmen Vidaurre,Carmen Vidaurre,Martijn Schreuder,Frank C. Meinecke,Paul von Bünau,Klaus-Robert Müller,Klaus-Robert Müller +7 more
TL;DR: This is the first generic theoretical formulation of the co-adaptive learning problem and gives a simple example of two interacting linear learning systems, a human and a machine, where the two learning agents are coupled by a joint loss function.
Book ChapterDOI
Learning to Predict the Leave-One-Out Error of Kernel Based Classifiers
TL;DR: An algorithm to predict the leave-one-out (LOO) error for kernel based classifiers is proposed, inspired by geometrical intuition and allows to reliably select a good model as demonstrated in simulations on Support Vector and Linear Programming Machines.
Journal ArticleDOI
N-ary decomposition for multi-class classification
TL;DR: It is theoretically shown that the proposed N-ary decomposition could be unified into the framework of error correcting output codes and give the generalization error bound of an N-ARY decomposition for multi-class classification.
Posted Content
iNNvestigate neural networks
Maximilian Alber,Sebastian Lapuschkin,Philipp Seegerer,Miriam Hägele,Kristof T. Schütt,Grégoire Montavon,Wojciech Samek,Klaus-Robert Müller,Sven Dähne,Pieter-Jan Kindermans +9 more
TL;DR: iNNvestigate as discussed by the authors provides a common interface and out-of-the-box implementation for many analysis methods, including the reference implementation for PatternNet and PatternAttribution as well as for LRP-methods.
Proceedings ArticleDOI
Brain-Computer Interfacing for multimedia quality assessment
TL;DR: An overview over the shortcomings of conventional approaches is given, the state-of-the art of BCI-based methods are presented and open questions and challenges relevant to the BCI community are discussed.