Geometry-Conditioned Hyperalignment for Generalizable EEG Decoding Across Datasets and Paradigms
Huu Hoang, Shanglin Li, Okito Yamashita…·Mitsuo Kawato
This paper introduces hTSMNet, a method for zero-shot EEG decoding across datasets and paradigms using geometry-conditioned hyperalignment and Riemannian SPD manifold learning.