Learn

This review paper provides the first comprehensive guide to the Voxelwise Encoding Model (VEM) framework. The VEM framework is a framework for fitting encoding models to fMRI data. This framework is currently the most sensitive and powerful approach available for modeling fMRI data. It can be used to fit dozens of distinct models simultaneously, each model having up to several thousand distinct features. The Voxelwise Encoding Model framework also conforms to all best practices in data science, which maximizes sensitivity, reliability and generalizability of the resulting models.

These Python tutorials show how to fit, evaluate, and interpret voxelwise encoding models on one of our public available datasets. We are providing these online tutorials here as a service to the fMRI community.

At the 2021 CCN meeting we held a keynote and tutorials session on the Voxelwise Encoding Model framework. You can find a video recording of the workshop here.

Encoding models identify the information represented in brain recordings, but fitting multiple models simultaneously presents several challenges. This paper (Dupre la tour et al., Neuroimage, 2022) describes how banded ridge regression can be used to solve these problems. Furthermore, several methods are proposed to address the computational challenge of fitting banded ridge regressions on large numbers of voxels and feature spaces. All implementations are released in an open-source Python package called Himalaya.