Reproduce “Compact Convolutional Neural Networks for Multi-Class, Personalised, Closed-Loop EEG-BCI” 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, Cedric Colas, Aldo Faisal
SmallNet enables four-class EEG control in BrainRunners by classifying Welch-estimated spectral-power features arranged by electrode layout, using a one-convolution CNN retrained on signals collected during play. For one BCI-naive volunteer, it achieved 47.6% ± 6.6% online accuracy, versus 25% chance. Game-trained cross-validation matched online accuracy, while video-trained scores exceeded gameplay, limiting conclusions to this participant and setting.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.