Explainable AI Insights Into EEG Classification and Its Alignment to Neural Correlates
Human Brain Mapping · 15.04.2026 · 47 (6)
DOI: 10.1002/hbm.70528 ↗Kurz gefasst
Fachartikel in der Zeitschrift Human Brain Mapping, online erschienen am 26.04.2026. Verfasst von Hendrik Eilts und 5 weiteren Autor:innen. Beteiligte Einrichtung: Cognitive Systems Lab, Universität Bremen, Bremen, Germany. Hauptthemen laut MEDLINE: Electroencephalography, Deep Learning, Attention, Auditory Perception. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft.
Abstract (Originalsprache)
While deep learning has drastically improved the performance of electroencephalography (EEG) analysis, it remains unclear what these models, such as EEGNet, learn from the data and how their learned features relate to neuroscientific concepts. In this work, we introduce a comprehensive interpretability framework for deep learning models of neural data based on Concept Relevance Propagation (CRP), an extension of layer‐wise relevance propagation that enables the analysis of abstract concepts encoded by individual neurons and filters. We apply CRP to individual filters of convolutional neural networks (EEGNet) trained using leave‐one‐out cross‐validation. To identify common classification strategies across models, we guide the selection of representative data for individual filters using relevance maximization, reduce dimensionality via UMAP, and identify clusters of filters encoding similar concepts through density‐based clustering. To gain insight into the neural correlates of these tasks, we analyze the learned features across multiple data domains without requiring model retraining. We integrate a virtual inspection layer to project explanations into the frequency domain, enabling the simultaneous analysis of spatial, temporal, and spectral aspects using topographic maps, functional grouping, and independent component analysis (ICA). Using three EEG classification tasks—auditory attention, internal/external attention, and motor imagery—we demonstrate that our approach reveals interpretable, task‐relevant neural patterns that generalize across participants. Overall, this framework provides a step toward understanding the models itself and gaining insights into the tasks in terms of neuroscience.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cognitive Systems Lab, Universität Bremen, Bremen, Germany.
- Statistical Methods in Epidemiology, Leibniz Institute for Prevention Research and Epidemiology-BIPS, Bremen, Germany.
Förderung
- Deutsche Forschungsgemeinschaft
Zitieren
APA
Eilts, H., Ivucic, G., Koenen, N., Wright, M. N., Schultz, T., & Putze, F. (2026). Explainable AI Insights Into EEG Classification and Its Alignment to Neural Correlates. Human Brain Mapping, 47(6). https://doi.org/10.1002/hbm.70528
Vancouver
Eilts H, Ivucic G, Koenen N, Wright MN, Schultz T, Putze F. Explainable AI Insights Into EEG Classification and Its Alignment to Neural Correlates. Human Brain Mapping. 2026;47(6). doi:10.1002/hbm.70528
BibTeX
@article{Eilts2026,
author = {Eilts, Hendrik and Ivucic, Gabriel and Koenen, Niklas and Wright, Marvin N and Schultz, Tanja and Putze, Felix},
title = {Explainable AI Insights Into EEG Classification and Its Alignment to Neural Correlates},
journal = {Human Brain Mapping},
year = {2026},
volume = {47},
number = {6},
doi = {10.1002/hbm.70528}
}
EUVIMED