Figure 2.

Classification performances of the DNN analysis

(A–C) This figure shows classification performances (i.e., accuracy) of the DNN analysis using behavioral data of test tasks during phases 1 (A), 2 (B), and both (C) with different feature-selecting methods (stepwise feature, significant between-genotype parameters, and all parameters). Asterisks (∗) denote the optimum cross-validated accuracy for the stepwise selection method. Black arrows represent classification results with gender also included as an input node. Error bars represent standard deviations of cross-validated accuracies. See also Figure S4.