NeurosciencebioRxivPreprint
Simple Geometric Recentering Rivals Deep Sequence Models for Cross-Session EEG Motor-Imagery Decoding
Meysam Rahimipour, Marc M. Van Hulle
This paper benchmarks deep sequence models against geometric baselines for cross-session EEG motor-imagery decoding, finding that a simple geometric approach outperforms complex models.
DOI 10.64898/2026.07.07.736991