Klaus-Robert Müller
119 publications
18 venues
H Index 51
Affiliation
Technical University of Berlin, GermanyLinks
DBLPGoogle Scholar
ORCID- https://web.ml.tu-berlin.de/author/prof.-dr.-klaus-robert-muller/
- https://dl.acm.org/profile/81100614579
- https://zbmath.org/authors/?q=ai:muller.klaus-robert
- https://mathscinet.ams.org/mathscinet/MRAuthorID/351427
- https://mathgenealogy.org/id.php?id=129531
- https://en.wikipedia.org/wiki/Klaus-Robert_M%C3%BCller
- https://www.wikidata.org/entity/Q26709023
- https://www.researcherid.com/rid/Y-3547-2019
- https://id.loc.gov/authorities/names/n98095050
- https://d-nb.info/gnd/1036485617
- https://d-nb.info/gnd/1202459374
- https://ieeexplore.ieee.org/author/37270663500
| Name | Venue | Year | citations |
|---|---|---|---|
MambaLRP: Explaining Selective State Space Sequence Models.
|
NIPS/NeurIPS | 2024 | 29 |
| xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology.
|
NIPS/NeurIPS | 2024 | 11 |
| Set Learning for Accurate and Calibrated Models.
|
ICLR | 2024 | 0 |
| Diffeomorphic Counterfactuals With Generative Models.
|
TPAMI | 2024 | 0 |
| Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces.
|
TPAMI | 2024 | 0 |
| Relevant Walk Search for Explaining Graph Neural Networks.
|
ICML | 2023 | 13 |
| Physics-Informed Bayesian Optimization of Variational Quantum Circuits.
|
NIPS/NeurIPS | 2023 | 0 |
| Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations.
|
CVPR | 2023 | 0 |
| Efficient Computation of Higher-Order Subgraph Attribution via Message Passing.
|
ICML | 2022 | 14 |
| XAI for Transformers: Better Explanations through Conservative Propagation.
|
ICML | 2022 | 134 |
| So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systems.
|
NIPS/NeurIPS | 2022 | 69 |
| Scrutinizing XAI using linear ground-truth data with suppressor variables.
|
MLJ | 2022 | 0 |
| Higher-Order Explanations of Graph Neural Networks via Relevant Walks.
|
TPAMI | 2022 | 0 |
| Building and Interpreting Deep Similarity Models.
|
TPAMI | 2022 | 0 |
| Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging.
|
NIPS/NeurIPS | 2021 | 9 |
| SE(3)-equivariant prediction of molecular wavefunctions and electronic densities.
|
NIPS/NeurIPS | 2021 | 121 |
| Explainable Deep One-Class Classification.
|
ICLR | 2021 | 0 |
| Fairwashing explanations with off-manifold detergent.
|
ICML | 2020 | 103 |
| Benign Examples: Imperceptible Changes Can Enhance Image Translation Performance.
|
AAAI | 2020 | 2 |
| Deep Semi-Supervised Anomaly Detection.
|
ICLR | 2020 | 0 |
| N-ary decomposition for multi-class classification.
|
MLJ | 2019 | 37 |
| Explanations can be manipulated and geometry is to blame.
|
NIPS/NeurIPS | 2019 | 371 |
| Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communication.
|
IJCNN | 2019 | 0 |
| Entropy-Constrained Training of Deep Neural Networks.
|
IJCNN | 2019 | 0 |
| Partial Optimality of Dual Decomposition for MAP Inference in Pairwise MRFs.
|
AISTATS | 2019 | 0 |
| iNNvestigate Neural Networks!
|
JMLR | 2019 | 0 |
| Curly: An AI-based Curling Robot Successfully Competing in the Olympic Discipline of Curling.
|
IJCAI | 2018 | 14 |
| An Empirical Study on The Properties of Random Bases for Kernel Methods.
|
NIPS/NeurIPS | 2017 | 15 |
| SchNet: A continuous-filter convolutional neural network for modeling quantum interactions.
|
NIPS/NeurIPS | 2017 | 1324 |
| Minimizing Trust Leaks for Robust Sybil Detection.
|
ICML | 2017 | 13 |
| An Easy-to-hard Learning Paradigm for Multiple Classes and Multiple Labels.
|
JMLR | 2017 | 101 |
| Wasserstein Training of Restricted Boltzmann Machines.
|
NIPS/NeurIPS | 2016 | 113 |
| The LRP Toolbox for Artificial Neural Networks.
|
JMLR | 2016 | 115 |
| Layer-Wise Relevance Propagation for Neural Networks with Local Renormalization Layers.
|
ICANN | 2016 | 527 |
| Analyzing Classifiers: Fisher Vectors and Deep Neural Networks.
|
CVPR | 2016 | 0 |
| Opening the Black Box: Revealing Interpretable Sequence Motifs in Kernel-Based Learning Algorithms.
|
ECML/PKDD | 2015 | 16 |
| Learning and Evaluation in Presence of Non-i.i.d. Label Noise.
|
AISTATS | 2014 | 27 |
| Covariance shrinkage for autocorrelated data.
|
NIPS/NeurIPS | 2014 | 21 |
| Generalizing Analytic Shrinkage for Arbitrary Covariance Structures.
|
NIPS/NeurIPS | 2013 | 17 |
| Robust Spatial Filtering with Beta Divergence.
|
NIPS/NeurIPS | 2013 | 48 |
| Regression for sets of polynomial equations.
|
AISTATS | 2012 | 1 |
| Deep Boltzmann Machines as Feed-Forward Hierarchies.
|
AISTATS | 2012 | 19 |
| Learning Invariant Representations of Molecules for Atomization Energy Prediction.
|
NIPS/NeurIPS | 2012 | 134 |
| Algebraic Geometric Comparison of Probability Distributions.
|
JMLR | 2012 | 0 |
| The Stationary Subspace Analysis Toolbox.
|
JMLR | 2011 | 17 |
| Kernel Analysis of Deep Networks.
|
JMLR | 2011 | 141 |
| ℓ
|
ICANN | 2011 | 0 |
| Layer-wise analysis of deep networks with Gaussian kernels.
|
NIPS/NeurIPS | 2010 | 25 |
| Approximate Tree Kernels.
|
JMLR | 2010 | 0 |
| Temporal kernel CCA and its application in multimodal neuronal data analysis.
|
MLJ | 2010 | 42 |
| How to Explain Individual Classification Decisions.
|
JMLR | 2010 | 0 |
| Subject independent EEG-based BCI decoding.
|
NIPS/NeurIPS | 2009 | 68 |
| Efficient and Accurate Lp-Norm Multiple Kernel Learning.
|
NIPS/NeurIPS | 2009 | 258 |
| On Relevant Dimensions in Kernel Feature Spaces.
|
JMLR | 2008 | 138 |
| Estimating vector fields using sparse basis field expansions.
|
NIPS/NeurIPS | 2008 | 25 |
| Playing Pinball with non-invasive BCI.
|
NIPS/NeurIPS | 2008 | 143 |
| Stopping conditions for exact computation of leave-one-out error in support vector machines.
|
ICML | 2008 | 5 |
| A Note on Brain Actuated Spelling with the Berlin Brain-Computer Interface.
|
HCI | 2007 | 111 |
| Asymptotic Bayesian generalization error when training and test distributions are different.
|
ICML | 2007 | 39 |
| Covariate Shift Adaptation by Importance Weighted Cross Validation.
|
JMLR | 2007 | 1040 |
| Optimal dyadic decision trees.
|
MLJ | 2007 | 54 |
| Invariant Common Spatial Patterns: Alleviating Nonstationarities in Brain-Computer Interfacing.
|
NIPS/NeurIPS | 2007 | 250 |
| The Need for Open Source Software in Machine Learning.
|
JMLR | 2007 | 242 |
| Machine Learning and Applications for Brain-Computer Interfacing.
|
HCI | 2007 | 28 |
| Heterogeneous Component Analysis.
|
NIPS/NeurIPS | 2007 | 3 |
| In Search of Non-Gaussian Components of a High-Dimensional Distribution.
|
JMLR | 2006 | 84 |
| Inducing Metric Violations in Human Similarity Judgements.
|
NIPS/NeurIPS | 2006 | 14 |
| Reducing Calibration Time For Brain-Computer Interfaces: A Clustering Approach.
|
NIPS/NeurIPS | 2006 | 77 |
| Incremental Support Vector Learning: Analysis, Implementation and Applications.
|
JMLR | 2006 | 379 |
| Logistic Regression for Single Trial EEG Classification.
|
NIPS/NeurIPS | 2006 | 93 |
| Denoising and Dimension Reduction in Feature Space.
|
NIPS/NeurIPS | 2006 | 15 |
| A Model Selection Method Based on Bound of Learning Coefficient.
|
ICANN | 2006 | 5 |
| Non-Gaussian Component Analysis: a Semi-parametric Framework for Linear Dimension Reduction.
|
NIPS/NeurIPS | 2005 | 14 |
| Model Selection Under Covariate Shift.
|
ICANN | 2005 | 35 |
| Analyzing Coupled Brain Sources: Distinguishing True from Spurious Interaction.
|
NIPS/NeurIPS | 2005 | 6 |
| Optimizing spatio-temporal filters for improving Brain-Computer Interfacing.
|
NIPS/NeurIPS | 2005 | 70 |
| Estimating Functions for Blind Separation When Sources Have Variance Dependencies.
|
JMLR | 2005 | 0 |
| Feature Discovery in Non-Metric Pairwise Data.
|
JMLR | 2004 | 111 |
| A Fast Algorithm for Joint Diagonalization with Non-orthogonal Transformations and its Application to Blind Source Separation.
|
JMLR | 2004 | 283 |
| Regularizing generalization error estimators: a novel approach to robust model selection.
|
ESANN | 2004 | 0 |
| Blind Separation of Post-nonlinear Mixtures using Linearizing Transformations and Temporal Decorrelation.
|
JMLR | 2003 | 79 |
| Feature Extraction for One-Class Classification.
|
ICANN | 2003 | 63 |
| Increase Information Transfer Rates in BCI by CSP Extension to Multi-class.
|
NIPS/NeurIPS | 2003 | 124 |
| Constructing Descriptive and Discriminative Nonlinear Features: Rayleigh Coefficients in Kernel Feature Spaces.
|
TPAMI | 2003 | 218 |
| Selecting Ridge Parameters in Infinite Dimensional Hypothesis Spaces.
|
ICANN | 2002 | 2 |
| The Subspace Information Criterion for Infinite Dimensional Hypothesis Spaces.
|
JMLR | 2002 | 22 |
| Combining Features for BCI.
|
NIPS/NeurIPS | 2002 | 78 |
| Constructing Boosting Algorithms from SVMs: An Application to One-Class Classification.
|
TPAMI | 2002 | 262 |
| Subspace information criterion for nonquadratic regularizers-Model selection for sparse regressors.
|
IEEE Trans. Neural Networks | 2002 | 5 |
| Going Metric: Denoising Pairwise Data.
|
NIPS/NeurIPS | 2002 | 74 |
| New Methods for Splice Site Recognition.
|
ICANN | 2002 | 79 |
| Clustering with the Fisher Score.
|
NIPS/NeurIPS | 2002 | 47 |
| Learning to Predict the Leave-One-Out Error of Kernel Based Classifiers.
|
ICANN | 2001 | 38 |
| Soft Margins for AdaBoost.
|
MLJ | 2001 | 1375 |
| A New Discriminative Kernel From Probabilistic Models.
|
NIPS/NeurIPS | 2001 | 157 |
| Kernel Feature Spaces and Nonlinear Blind Souce Separation.
|
NIPS/NeurIPS | 2001 | 32 |
| Classifying Single Trial EEG: Towards Brain Computer Interfacing.
|
NIPS/NeurIPS | 2001 | 561 |
| Estimating the Reliability of ICA Projections.
|
NIPS/NeurIPS | 2001 | 16 |
| An introduction to kernel-based learning algorithms.
|
IEEE Trans. Neural Networks | 2001 | 3766 |
| Robust Ensemble Learning for Data Mining.
|
PAKDD | 2000 | 24 |
| Barrier Boosting.
|
COLT | 2000 | 40 |
| A Mathematical Programming Approach to the Kernel Fisher Algorithm.
|
NIPS/NeurIPS | 2000 | 200 |
| Unmixing Hyperspectral Data.
|
NIPS/NeurIPS | 1999 | 170 |
| v-Arc: Ensemble Learning in the Presence of Outliers.
|
NIPS/NeurIPS | 1999 | 18 |
| Tools for computer-supported learning in organisations.
|
HCI | 1999 | 0 |
| Input space versus feature space in kernel-based methods.
|
IEEE Trans. Neural Networks | 1999 | 1313 |
| Hidden Markov gating for prediction of change points in switching dynamical systems.
|
ESANN | 1999 | 3 |
| Invariant Feature Extraction and Classification in Kernel Spaces.
|
NIPS/NeurIPS | 1999 | 211 |
| Regularizing AdaBoost.
|
NIPS/NeurIPS | 1998 | 58 |
| Kernel PCA and De-Noising in Feature Spaces.
|
NIPS/NeurIPS | 1998 | 1150 |
| Analysis of Wake/Sleep EEG with Competing Experts.
|
ICANN | 1997 | 5 |
| Kernel Principal Component Analysis.
|
ICANN | 1997 | 2701 |
| Asymptotic statistical theory of overtraining and cross-validation.
|
IEEE Trans. Neural Networks | 1997 | 380 |
| Analysis of Drifting Dynamics with Neural Network Hidden Markov Models.
|
NIPS/NeurIPS | 1997 | 14 |
| Predicting Time Series with Support Vector Machines.
|
ICANN | 1997 | 1067 |
| Prediction of Mixtures.
|
ICANN | 1996 | 6 |
| Analysis of Drifting Dynamics with Competing Predictors.
|
ICANN | 1996 | 1 |
| Adaptive On-line Learning in Changing Environments.
|
NIPS/NeurIPS | 1996 | 92 |
| Statistical Theory of Overtraining - Is Cross-Validation Asymptotically Effective?
|
NIPS/NeurIPS | 1995 | 83 |