Uncertainty Quantification for cross-subject Motor Imagery classification
This work addresses the challenge of inter-subject variability in brain-computer interfaces, but it is incremental as it applies existing uncertainty quantification methods to a specific domain.
The paper tackled the problem of predicting misclassifications in cross-subject motor imagery classification using uncertainty quantification methods, finding that Deep Ensembles performed best in both classification and uncertainty quantification, while standard CNNs with Softmax output outperformed some advanced methods.
Uncertainty Quantification aims to determine when the prediction from a Machine Learning model is likely to be wrong. Computer Vision research has explored methods for determining epistemic uncertainty (also known as model uncertainty), which should correspond with generalisation error. These methods theoretically allow to predict misclassifications due to inter-subject variability. We applied a variety of Uncertainty Quantification methods to predict misclassifications for a Motor Imagery Brain Computer Interface. Deep Ensembles performed best, both in terms of classification performance and cross-subject Uncertainty Quantification performance. However, we found that standard CNNs with Softmax output performed better than some of the more advanced methods.