Number of training examples:    1000
Number of validation examples:  5000 (for model selection)
Number of test examples:       10000

1) error rate

a) for all 5 runs
    0.0456    0.0436    0.0438    0.0469    0.0427

b) mean
    0.0445

c) standard deviation
    0.0017

2) specificity ( 1 - false positives )

a) for all 5 runs
    0.9708    0.9638    0.9595    0.9786    0.9650

b) mean

    0.9675

c) standard deviation
    0.0074

3) sensitivity (true positives)

a) for all 5 runs
    0.9280    0.9441    0.9510    0.9103    0.9444

b) mean
    0.9355

c) standard deviation
    0.0165