Clustered Gaussian Graphical Model via Symmetric Convex Clustering

However, accurately determining connectivity is not directly observable, numerous techniques which neurons carry out similar neurological tasks via controlled such as correlations and partial correlations have been proposed experiments is both labor-intensive and prohibitively to estimate such functional connectivity from neural expensive on a large scale. Thus, it is of great interest to recording data (see [3] for a comprehensive review). In this cluster neurons that have similar connectivity profiles into work, we define functional connectivity between each pair of functionally coherent groups in a data-driven manner. In this recorded neurons to be their pairwise partial correlation or work, we propose the clustered Gaussian graphical model edges in an undirected GGM in high dimensions. Because (GGM) and a novel symmetric convex clustering penalty the pairwise partial correlation between two neurons takes in an unified convex optimization framework for inferring activities of all the other recorded neurons into account, it functional clusters among neurons from neural activity data.