Reproduce “CNNATT: Deep EEG & fNIRS Real-Time Decoding of bimanual forces” 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
Pablo Ortega, Tong Zhao, Aldo Faisal
The cnnatt model reconstructs continuous left- and right-hand grip-force trajectories from EEG and fNIRS during a laboratory task. It combines convolutional neural-network layers with self-attention and uses the preceding 800 milliseconds of data. For the left hand it scores 54.2% on FVAF versus 46.9% for Lasso; cnnatt scores higher for both hands in ten healthy participants, not people with paralysis.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.