An Empirical Comparison Of Deep Learning Explainability Approaches For Eeg Using Simulated Ground Truth

This study examines the interpretability of deep learning (DL) models used in scalp electroencephalography (EEG) based Brain-Computer Interface (BCI) systems. A simulation framework was developed to evaluate the robustness and sensitivity of twelve back-propagation-based visualization methods by comparing to ground truth features. Results showed that DeepLift was consistently accurate as well as robust to detect the three key attributes tested here (temporal, spatial, and spectral precision). This study provides a review of model explanation methods for DL-based neural decoders and recommendations to understand when some of these methods fail and what they can capture in EEG.