New avenues for understanding what deep networks learn from EEG.

ABSTRACT: An important but unresolved question in deep learning for EEG decoding is which features neural networks learn to solve the task. Prior interpretability studies have mainly explained individual predictions, analyzed the use of established EEG features, or examined subnetworks of larger models. In contrast, we apply interpretability methods to uncover features learned by the complete network. Specifically, we introduce two complementary architectures with dedicated visualization techniques to obtain an approximate understanding of the full network trained on binary classification into nonpathological and pathological EEG. First, we use invertible networks-networks that are designed to be invertible-to generate prototypical input signals for each class. Second, we design a very compact netwo

SUBMITTER: Schirrmeister RT 

PROVIDER: S-EPMC12545007 | biostudies-literature | 2025

REPOSITORIES: biostudies-literature