Reproduce “Band2Net: Frequency-to-Network Transport Distillation for fMRI-Privileged, EEG-Only Session-Condition Decoding” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Nishi Kanta Paul, Md Shihabul Islam Shovo, Dwarikanath Mahapatra
Band2Net uses fMRI network information to guide EEG training, then makes session-condition predictions from EEG alone. During training, a learned transport plan matches five EEG rhythm representations to seven fMRI network representations in participant-, session-, and context-matched recordings acquired separately. In a 56-participant dataset, it achieved ROC-AUC 0.801 versus 0.751 for an EEG-only student; this supports session-condition decoding, not a biomarker.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.