To better map hierarchical brain connectivity networks, we introduce a novel class of deep (multilayer) linear models of fMRI that bridge the gap between conventional methods such as independent component analysis and more complex deep nonlinear models. These deep linear models do not require the manual hyperparameter tuning, extensive fMRI training data or high-performance computing infrastructure needed by deep learning, such as convolutional neural networks, and their results are more explainable from their mathematical structure. These benefits gain in importance as continual improvements in the spatial and temporal resolution of fMRI reveal more of the hierarchy of spatiotemporal brain architecture.
This abstract and the presentation materials are available to members only; a login is required.