Skip to content

Latest commit

 

History

History
4 lines (4 loc) · 370 Bytes

File metadata and controls

4 lines (4 loc) · 370 Bytes

Brain.io 2023 Hackathon April 22-23 Third Place Data Analysis Code (uncleaned)

Identified types of objects seen in a video by subjects from corresponding ECoG data.
The most useful feature- and label-related tools used include common spatial patterns, LDA, SHAP values, and CLIP.
The most useful ML models were k-NN, gradient boosting trees, and random forest.