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
Journal ArticleDOI

Blind source separation techniques for decomposing event-related brain signals

Klaus-Robert Müller, +3 more
- 01 Feb 2004 - 
TL;DR: The concept of BSS is reviewed and its usefulness in the context of event-related MEG measurements is demonstrated and an additional grouping of the BSS components reveals interesting structure, that could ultimately be used for gaining a better physiological modeling of the data.
Book ChapterDOI

Explaining and Interpreting LSTMs

Leila Arras, +9 more
TL;DR: This chapter explores how to adapt the Layer-wise Relevance Propagation technique used for explaining the predictions of feed-forward networks to the LSTM architecture used for sequential data modeling and forecasting.
Journal ArticleDOI

Localizing and estimating causal relations of interacting brain rhythms.

Guido Nolte, +1 more
- 22 Nov 2010 - 
TL;DR: A number of methods that allow for addressing brain connectivity and especially causality between different brain regions from EEG or MEG are reviewed, all based on the insight that the imaginary part of the cross-spectra cannot be explained as a mixing artifact.
Journal ArticleDOI

Analyzing Local Structure in Kernel-Based Learning: Explanation, Complexity, and Reliability Assessment

Grégoire Montavon, +3 more
- 12 Jun 2013 - 
TL;DR: A set of recent methods that can be universally used to make kernel methods more transparent are reported on that allows to assess the underlying complexity and noise structure of a learning problem and thus to distinguish high/low noise scenarios of high/ low complexity respectively.
Posted ContentDOI

Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology

Stefan Studer, +6 more
TL;DR: This work proposes a process model for the development of machine learning applications and expands on CRISP-DM, a data mining process model that enjoys strong industry support but lacks to address machine learning specific tasks.