H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 151 Citations 102,859 665 World Ranking 10 National Ranking 1

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Statistics

Klaus-Robert Müller mostly deals with Artificial intelligence, Machine learning, Brain–computer interface, Pattern recognition and Electroencephalography. His biological study spans a wide range of topics, including Set and Molecular dynamics. His work carried out in the field of Machine learning brings together such families of science as Electronic structure, Potential energy and Density functional theory.

His Brain–computer interface study combines topics in areas such as Field, Human–computer interaction, Adaptation and Interfacing. As a part of the same scientific study, Klaus-Robert Müller usually deals with the Electroencephalography, concentrating on Speech recognition and frequently concerns with Signal processing and Boosting. His studies deal with areas such as Contextual image classification and Convolutional neural network as well as Artificial neural network.

His most cited work include:

  • Nonlinear component analysis as a kernel eigenvalue problem (6463 citations)
  • An introduction to kernel-based learning algorithms (3027 citations)
  • Efficient BackProp (1396 citations)

What are the main themes of his work throughout his whole career to date?

His scientific interests lie mostly in Artificial intelligence, Machine learning, Pattern recognition, Artificial neural network and Brain–computer interface. Klaus-Robert Müller combines subjects such as Relevance and Computer vision with his study of Artificial intelligence. His Machine learning research incorporates themes from Electronic structure, Set, Density functional theory and Molecular dynamics.

Klaus-Robert Müller has included themes like Algorithm and Interpretability in his Artificial neural network study. His work deals with themes such as Interfacing and Human–computer interaction, which intersect with Brain–computer interface. His Electroencephalography research includes elements of Neurophysiology and Speech recognition.

He most often published in these fields:

  • Artificial intelligence (93.60%)
  • Machine learning (48.90%)
  • Pattern recognition (28.54%)

What were the highlights of his more recent work (between 2019-2021)?

  • Artificial intelligence (93.60%)
  • Machine learning (48.90%)
  • Artificial neural network (33.37%)

In recent papers he was focusing on the following fields of study:

Klaus-Robert Müller spends much of his time researching Artificial intelligence, Machine learning, Artificial neural network, Deep learning and Molecular dynamics. Klaus-Robert Müller interconnects Field and Pattern recognition in the investigation of issues within Artificial intelligence. His Pattern recognition study combines topics from a wide range of disciplines, such as Image and Electroencephalography.

His research in Machine learning intersects with topics in Ab initio, Quantum, Robustness and Molecular mechanics. The concepts of his Artificial neural network study are interwoven with issues in Domain, Relevance, Granularity, Range and Algorithm. His research integrates issues of Focus, Molecule, Interface and Density functional theory in his study of Molecular dynamics.

Between 2019 and 2021, his most popular works were:

  • Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data (164 citations)
  • Machine Learning for Molecular Simulation. (91 citations)
  • Machine Learning for Molecular Simulation. (91 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Statistics
  • Machine learning

His main research concerns Artificial intelligence, Machine learning, Artificial neural network, Deep learning and Molecular dynamics. His study in Artificial intelligence focuses on Interpretability in particular. His Machine learning research is multidisciplinary, incorporating elements of Molecule, Quantum chemical, Homogeneous space, Ab initio and Test data.

The various areas that Klaus-Robert Müller examines in his Artificial neural network study include Anomaly detection, Graph neural networks, Graph, Algorithm and Generative grammar. His Deep learning study deals with Data modeling intersecting with Relation, Variety, Data science, Feature extraction and Similarity. His study in Molecular dynamics is interdisciplinary in nature, drawing from both Focus, Granularity, Leverage and Interface.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

Nonlinear component analysis as a kernel eigenvalue problem

Bernhard Schölkopf;Alexander Smola;Klaus-Robert Müller.
Neural Computation (1998)

9108 Citations

An introduction to kernel-based learning algorithms

K.-R. Muller;S. Mika;G. Ratsch;K. Tsuda.
IEEE Transactions on Neural Networks (2001)

4404 Citations

Efficient BackProp

Yann LeCun;Léon Bottou;Genevieve B. Orr;Klaus-Robert Müller.
neural information processing systems (1998)

3747 Citations

Kernel Principal Component Analysis

Bernhard Schölkopf;Alexander J. Smola;Klaus-Robert Müller.
international conference on artificial neural networks (1997)

2381 Citations

Optimizing Spatial filters for Robust EEG Single-Trial Analysis

B. Blankertz;R. Tomioka;S. Lemm;M. Kawanabe.
IEEE Signal Processing Magazine (2008)

1673 Citations

Input space versus feature space in kernel-based methods

B. Scholkopf;S. Mika;C.J.C. Burges;P. Knirsch.
IEEE Transactions on Neural Networks (1999)

1542 Citations

Soft Margins for AdaBoost

G. Rätsch;T. Onoda;K.-R. Müller.
Machine Learning (2001)

1448 Citations

Predicting Time Series with Support Vector Machines

Klaus-Robert Müller;Alex J. Smola;Gunnar Rätsch;Bernhard Schölkopf.
international conference on artificial neural networks (1997)

1196 Citations

Kernel PCA and De-Noising in Feature Spaces

Sebastian Mika;Bernhard Schölkopf;Alex J. Smola;Klaus-Robert Müller.
neural information processing systems (1998)

1189 Citations

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation.

Sebastian Bach;Alexander Binder;Grégoire Montavon;Frederick Klauschen.
PLOS ONE (2015)

1152 Citations

If you think any of the details on this page are incorrect, let us know.

Contact us

Best Scientists Citing Klaus-Robert Müller

Cuntai Guan

Cuntai Guan

Nanyang Technological University

Publications: 152

Bernhard Schölkopf

Bernhard Schölkopf

Max Planck Institute for Intelligent Systems

Publications: 123

Masashi Sugiyama

Masashi Sugiyama

University of Tokyo

Publications: 113

Seong-Whan Lee

Seong-Whan Lee

Korea University

Publications: 102

Gernot R. Müller-Putz

Gernot R. Müller-Putz

Graz University of Technology

Publications: 101

Andrzej Cichocki

Andrzej Cichocki

Skolkovo Institute of Science and Technology

Publications: 99

Kai Keng Ang

Kai Keng Ang

Agency for Science, Technology and Research

Publications: 95

Dario Farina

Dario Farina

Imperial College London

Publications: 93

Benjamin Blankertz

Benjamin Blankertz

Technical University of Berlin

Publications: 90

José del R. Millán

José del R. Millán

The University of Texas at Austin

Publications: 89

Andrea Kübler

Andrea Kübler

University of Würzburg

Publications: 86

Fabien Lotte

Fabien Lotte

French Institute for Research in Computer Science and Automation - INRIA

Publications: 85

Jose C. Principe

Jose C. Principe

University of Florida

Publications: 85

Johan A. K. Suykens

Johan A. K. Suykens

KU Leuven

Publications: 85

Vadim V. Nikulin

Vadim V. Nikulin

Max Planck Society

Publications: 74

Gene Cheung

Gene Cheung

York University

Publications: 58

Something went wrong. Please try again later.