Unsupervised Feature Learning Improves Prediction of Human Brain Activity in Response to Natural Images
The encoding performance was defined as between the observed and predicted voxel responses to the 120 images in the validation set across the two subjects. The encoding performance of the SC2 model was significantly higher than that of the GWP2 model. (A) Prediction across the voxels that survived the threshold of 0.1. (B) Mean prediction across the voxels that survived the threshold of 0.1. Error bars show 1 SEM across the voxels (bootstrapping method). (C) Prediction in each voxel.