… machine learning algorithm (kernel regression) in predicting … The weights are the trainable
parameters in FNN. The … a curated set of 13 HCP cognitive measures averaged across 20 test …

… on machine learning as applied to functional connectivity with … -level predictions about
patients with machine learning, providing … For example, the reliability of functional connectivity is …

… Accurate identification of the altered functional connectivity … , after predicting functional
connectivity using deep learning, … In order to evaluate the importance of functional connectivity …

… focused on employing novel deep learning algorithms, which takes the … prediction is more
accurate than that of any individual tree. … In summary, our work illustrates the importance of site…

… and the reliability of our method. … features which occur more than 500 times in training step
during 100 times 10-fold CV, the connections between bilateral mOFC had the highest weight …

… brain network organization, yet the functional importance of … connectivity-based models to
predict independent cognitive … provide more accurate task-evoked activation predictions with …

… machine learning algorithms and the functional connections of … been challenging and
identifying reliable non-invasive brain … used to estimate the weights of the features for the patient …

… predicted functional connectivity from structural connectivity … cognition with comparable
accuracy to empirical functional … accurate to date (group: r = 0.9 ± 0.1 , individual: r = 0.55 ± 0.1 ). …

… we average the neural network weights over last 20 epochs. … of machine learning models
of functional connectivity, we … yield predictions that are significantly more robust and accurate …

… that task-based machine learning models often outperformed … and reliability, we repeated
the prediction procedure 100 … contribution of each functional network to prediction, we grouped …