W10-3204 we can obtain three groups of two-fold cross-validation data sets . Estimating the parameter
S13-1033 whole training set by means of two-fold cross-validation . The individual and global results
P13-1039 models , tuning hyperparameters by two-fold cross-validation . We then extracted noun phrase
W10-3204 experiments , three groups of two-fold cross-validation sets are used to estimate the
N13-1112 -- 5 ) for testing . We perform two-fold cross-validation experiments using the two test
W10-3204 ) model to train and test on a two-fold cross-validation data set . The extracted features
W05-0609 the three sets and ten runs of two-fold cross-validation for each of them . For SDC ,
W13-2220 regularization parameter C is chosen by two-fold cross-validation . In practice , subsampling of
J10-2002 reported here is the average of two-fold cross-validation . We compared three methods :
N13-1112 and Discussion Table 3 shows the two-fold cross-validation results for our 14-class temporal
D15-1054 0.2 through grid search based on two-fold cross-validation . This small value indeed verifies
W05-0405 articles in half , and perform two-fold cross-validation as recommended by Dietterich
J11-1007 explained in Section 5 , with two-fold cross-validation when parsing the training data
N12-1003 halves and conducted tests with two-fold cross-validation . We tested thresholds for the
W10-1746 2002 ) with a RBF ker - nel . Two-fold cross-validation was done to prevent over-fitting
hide detail