Chethan Pandarinath @chethanp.bsky.social · Dec 3 How can we build BCIs that operate robustly in the face of nonstationarities? Our @neuripsconf.bsky.social Datasets and Benchmarks paper introduces the Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark! Led by Brianna Karpowicz and @joelye.bsky.social
36 likes 1 replies
?
Replies
We include open datasets and standardized metrics to evaluate BCI decoding performance. Together with AE Studios, we implement a flexible evaluation platform that only requires user-submitted code to return behavioral predictions on unseen data. Summary vid: www.youtube.com/watch?v=1dd7...