Interpretable EEG biomarkers with bag-of-waves: Spatial and temporal waveform dictionaries for low-data regimes

Athanasios Papastathopoulos-Katsaros, Steven T. Lee, Lin Yao, Ajay Thomas, Junseok Park et al.|July 24, 2026arXiv

Key Takeaway

For EEG analysis in low-data settings, learning interpretable waveform dictionaries can match deep learning performance while using far fewer parameters and providing clinically meaningful explanations.

Summary

Bag-of-waves is an interpretable EEG analysis method that learns a small dictionary of recurring waveform patterns (atoms) without labels, then represents brain signals as sequences of these patterns.

efficiency

Key Terms

bag-of-waves shift-invariant-clustering waveform-atoms n-grams