Klaus- Robert Müller
Impact in
- Cognitive Neuroscience top 0.02%
- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Signal Processing top 0.02%
- Blind Source Separation Techniques
Papers in
-
- EEG and Brain-Computer Interfaces 160
- Neural dynamics and brain function 104
-
- Blind Source Separation Techniques 74
- Co-authors
- Bernhard Schölkopf (13 shared papers)Alexander Johannes Smola (7 shared papers)Wojciech Samek (77 shared papers)Grégoire Montavon (50 shared papers)Benjamin Blankertz (62 shared papers)Alexander Binder (22 shared papers)Alexandre Tkatchenko (26 shared papers)Sebastian Lapuschkin (15 shared papers)
- Journals
- NeuroImage (26 papers)PLoS ONE (21 papers)Journal of Neural Engineering (17 papers)IEEE Transactions on Neural Networks and Learning Systems (10 papers)Neural Computation (8 papers)
- Partner nations
- GermanySouth KoreaUnited States
In The Last Decade
Klaus- Robert Müller
477 papers receiving 50.3k citations
Klaus- Robert Müller's Hit Papers
Peers
Comparison fields: 5 of 228
- Cognitive Neuroscience 16.0k
- Signal Processing 6.1k
- Health Informatics 750
- Artificial Intelligence 14.8k
- Computer Vision and Pattern Recognition 8.3k
Countries citing papers authored by Klaus- Robert Müller
This map shows the geographic impact of Klaus- Robert Müller's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Klaus- Robert Müller with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Klaus- Robert Müller more than expected).
Fields of papers citing papers by Klaus- Robert Müller
This network shows the impact of papers produced by Klaus- Robert Müller. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Klaus- Robert Müller. The network helps show where Klaus- Robert Müller may publish in the future.
Co-authors
The 25 scholars most cited alongside Klaus- Robert Müller, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 496 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | Nonlinear Component Analysis as a Kernel Eigenvalue Problem Hit paper breakdown → | 1998 | 6172 |
| 2 | On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation Hit paper breakdown → | 2015 | 3144 |
| 3 | Methods for interpreting and understanding deep neural networks Hit paper breakdown → | 2017 | 1869 |
| 4 | Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning Hit paper breakdown → | 2012 | 1738 |
| 5 | Optimizing Spatial filters for Robust EEG Single-Trial Analysis Hit paper breakdown → | 2008 | 1683 |
| 6 | Kernel principal component analysis Hit paper breakdown → | 1997 | 1440 |
| 7 | Efficient BackProp Hit paper breakdown → | 1998 | 1082 |
| 8 | Efficient BackProp Hit paper breakdown → | 2012 | 975 |
| 9 | Explaining nonlinear classification decisions with deep Taylor decomposition Hit paper breakdown → | 2016 | 974 |
| 10 | Single-trial analysis and classification of ERP components — A tutorial Hit paper breakdown → | 2010 | 940 |
| 11 | Review of the BCI Competition IV Hit paper breakdown → | 2012 | 938 |
| 12 | Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications Hit paper breakdown → | 2021 | 909 |
| 13 | Machine learning of accurate energy-conserving molecular force fields Hit paper breakdown → | 2017 | 904 |
| 14 | The non-invasive Berlin Brain–Computer Interface: Fast acquisition of effective performance in untrained subjects Hit paper breakdown → | 2007 | 796 |
| 15 | Evaluating the Visualization of What a Deep Neural Network Has Learned Hit paper breakdown → | 2016 | 785 |
| 16 | Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space Hit paper breakdown → | 2015 | 653 |
| 17 | Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems Hit paper breakdown → | 2021 | 641 |
| 18 | Kernel PCA and De-Noising in Feature Spaces | 1998 | 633 |
| 19 | 2010 | 566 | |
| 20 | Layer-Wise Relevance Propagation: An Overview Hit paper breakdown → | 2019 | 522 |
About Klaus- Robert Müller
Klaus- Robert Müller is a scholar working on Cognitive Neuroscience, Signal Processing, Artificial Intelligence, Cellular and Molecular Neuroscience and Computer Vision and Pattern Recognition, having authored 496 papers that have together received 52.0k indexed citations. Recurring topics across this work include EEG and Brain-Computer Interfaces (160 papers), Neural dynamics and brain function (104 papers), Blind Source Separation Techniques (74 papers), Neuroscience and Neural Engineering (65 papers), Machine Learning in Materials Science (60 papers), Neural Networks and Applications (55 papers), Computational Drug Discovery Methods (42 papers) and Explainable Artificial Intelligence (XAI) (39 papers). The work is most often cited by research in Cognitive Neuroscience (16.0k citations), Signal Processing (6.1k citations), Health Informatics (750 citations), Artificial Intelligence (14.8k citations) and Computer Vision and Pattern Recognition (8.3k citations). Klaus- Robert Müller has collaborated with scholars based in Germany, South Korea and United States. Frequent co-authors include Bernhard Schölkopf, Alexander Johannes Smola, Wojciech Samek, Grégoire Montavon, Benjamin Blankertz, Alexander Binder, Alexandre Tkatchenko, Sebastian Lapuschkin, Gabriel Curio and Steven Lemm. Their work appears in journals such as NeuroImage, PLoS ONE, Journal of Neural Engineering, IEEE Transactions on Neural Networks and Learning Systems and Neural Computation.
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.