Klaus‐Robert Müller

This paper introduces a bidirectional recurrent model of attention inspired by biological mechanisms and neural networks, capable of replicating behavioral and neural findings related to visual attention.

This paper introduces a method to infer signaling pathway activities from H&E slides in HNSCC, revealing two prognostic tumor states.

The paper compares re-referencing and spectral analysis techniques to estimate BSEP source locations in sEEG data from human subjects.

This study uses explainable AI to link brain-age prediction models with neuroimaging features of aging, revealing correlations between voxel relevance and structural brain markers.

This paper introduces a method to quantify and compare brain stimulation response shapes using canonical response parameterization, enabling statistical analysis of single-pulse intracranial electrical stimulation data.

The paper develops a hierarchical Bayesian model for EEG source reconstruction that jointly estimates full-structure noise covariance matrices, improving accuracy in real-world scenarios with non-diagonal noise.

This paper uses deep learning to estimate brain age from MRI data and identifies structural brain changes associated with aging.

Harmoni removes spurious neuronal interactions caused by harmonic components in EEG data, improving the detection of genuine cross-frequency synchronization.

This paper introduces a data-driven method to identify basis profile curves from brain stimulation responses, enabling interpretation of neural interactions in human brain networks.

This paper unifies three sparse Bayesian learning algorithms for EEG/MEG brain source imaging under the majorization-minimization framework and introduces a new method for low SNR settings and noise variance estimation.

DeepCOMBI uses explainable AI to enhance GWAS analysis by identifying relevant genetic loci and outperforming traditional methods in power and precision.

This study identifies sensorimotor functional connectivity as a neurophysiological factor correlated with BCI performance, showing its significance beyond oscillation amplitude.

This paper introduces NID, a method to decompose cross-frequency coupled sources in EEG/MEG data, showing it reliably extracts nonlinear interactions even at low SNR and identifies alpha-beta phase-phase coupling in resting-state EEG.