In these frameworks, templates are constructed using an iterative process of template estimation and alignment, which is often computationally very expensive. Due in part to this shortcoming, most methods compute asingle template for the entire population of images, or a few templates for specific sub-groups of the data.

Each voxel in a diffusion MRI (dMRI) image contains a spherical signal corresponding to the direction and strength of water diffusion in the brain.

Thus, fMRI BOLD activity reflects an indirect, noisy measure ofneural activity,mismatched toneural timescales byseveral orders ofmagnitude.

Finally,an EEG forward model based onapre-estimated lead field matrix wasconstructed together with the ROIsource model togenerate scalp EEG observations.

Let usconsiderasetof C-PROcontextswithlogicrules BOTHor EITHER, andsensoryruleswith values REDor VERTICAL (Figure 1).

Here, we propose a hybrid model, the Hyper-HMM, that simultaneously aligns both temporal and spatial features across brains.

Inthis work, we study Transformer-based models for brain network analysis.

However,theaggregationofdata coming from multiple subjects is challenging, since it requires accounting for largevariability inanatomy,functional topographyandstimulus response across individuals.