Carlos Ernesto Garrido Salmón

This paper uses machine learning to predict TMS stimulation sites using tractography and myographic responses, showing improved performance in some subjects.

This study applies deep learning to resting-state fMRI time series to predict 58 human traits, finding comparable performance to kernel-based methods with some advantages in robustness to training set size reductions.

This paper reviews methods for predicting human intelligence from neuroimaging data, finding differences in performance between general and fluid intelligence predictions.

This study evaluates the long-term effects of network-based fMRI neurofeedback training on sustained attention, finding lasting neural changes but transient behavioral improvements.