Is k-folds cross-valiation in regressionlearner random or block/leave one out?

Is the k-folds cross-valiation in the regressionlearner random or block/leave one out? The documentation does not say.

If random, does MATLAB have functionality to complete block/leave one out cross-validation?

Answer 1

[Drew]

You can perform leave-one-out cross-validation in Regression Learner by setting the number of cross-validation folds equal to the number of samples in your training set. At the session start dialogue, you will find that the number of samples in the training set is the maximum allowed value for the number of folds.