<ul><li>Researchers have developed a novel geometric framework that uses diffeomorphic transformations to embed correlation matrices into a Euclidean space.</li><li>The proposed method improves computational speed and enhances accuracy compared to conventional manifold-based approaches.</li><li>This framework has been applied to behavior score prediction, subject fingerprinting in resting-state fMRI, and hypothesis testing in electroencephalogram data.</li><li>An open-source MATLAB toolbox is provided to facilitate broader adoption and advance the application of correlation geometry in functional brain network research.</li></ul>

Scalable Geometric Learning with Correlation-Based Functional Brain Networks

Discover more