Reproduce “Graph Neural Networks Uncover Geometric Neural Representations in Reinforcement-Based Motor Learning” 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
Federico Nardi, Jinpei Han, Shlomi Haar, A.Aldo Faisal
The authors use a graph neural network to predict whether EEG before a pool shot contains information about the previous shot’s outcome. They connect nearby electrodes in a spatial graph and pretrain on related groups before target-group training. On balanced error-feedback data, four-group mean validation accuracy rises from 0.54 without pretraining to 0.65 with opposite-round pretraining; evaluation uses cross-validation, not external testing.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.