Reproduce “Model-Agnostic Meta-Learning for EEG Motor Imagery Decoding in Brain-Computer-Interfacing” 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
Denghao Li, Pablo Ortega, Xiaoxi Wei, Aldo Faisal
The authors apply model-agnostic meta-learning to EEG motor-imagery decoding, training a shared model initialization to adapt to a new person with task-specific data. On PhysioNet, meta-learning outperformed transfer learning on reported tasks; for imagined left- versus right-fist classification, test accuracy was 64.5%, compared with 56.0% and 59.6% for transfer and conventional learning. Confidence filtering and unclear evaluation details limit the result.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.