• Publications
  • Influence
Multiclass Common Spatial Patterns and Information Theoretic Feature Extraction
It is pointed out that CSP by joint approximate diagonalization (JAD) is equivalent to independent component analysis (ICA), and a method to choose those independent components (ICs) that approximately maximize mutual information of ICs and class labels is provided. Expand
Quantifying causal influences
Many methods for causal inference generate directed acyclic graphs (DAGs) that formalize causal relations between $n$ variables. Given the joint distribution on all these variables, the DAG containsExpand
Crowdsourced analysis of clinical trial data to predict amyotrophic lateral sclerosis progression
The DREAM-Phil Bowen ALS Prediction Prize4Life challenge identified several potential nonstandard predictors of disease progression including uric acid, creatinine and surprisingly, blood pressure, shedding light on ALS pathobiology. Expand
Causal influence of gamma oscillations on the sensorimotor rhythm
It is demonstrated that gamma oscillations have a causal influence on a subject's capability to utilize a BCI for means of communication, and is of particular importance for brain-computer interfaces (BCIs). Expand
Transfer Learning in Brain-Computer Interfaces
A framework for transfer learning in the context of BCIs that can be applied to any arbitrary feature space, as well as a novel regression estimation method that is specifically designed for the structure of a system based on the electroencephalogram (EEG). Expand
Causal interpretation rules for encoding and decoding models in neuroimaging
It is shown that only encoding models in the stimulus-based setting support unambiguous causal interpretations, and combined encoding and decoding models trained on the same data obtain insights into causal relations beyond those that are implied by each individual model type. Expand
Biased feedback in brain-computer interfaces
It is indicated that subjects already capable of operating a BCI are impeded by inaccurate feedback, while subjects normally performing on or close to chance level may actually benefit from an incorrect belief on their performance level. Expand
Critical issues in state-of-the-art brain-computer interface signal processing.
The relationship between electroencephalography and electrocorticography, novel features for performance prediction, time-embedded signal representations, phase information, signal non-stationarity, and unsupervised adaptation are presented. Expand
Multitask Learning for Brain-Computer Interfaces
This paper utilizes the framework of multitask learning to construct a BCI that can be used without any subject-specific calibration process, and shows that satisfactory classification results can be achieved with zero training data. Expand
Multisubject Learning for Common Spatial Patterns in Motor-Imagery BCI
The details of the multitask CSP algorithm are outlined, results on two data sets are shown and a clear improvement can be seen, especially when the number of training trials is relatively low. Expand