Number of training examples:     100
Number of validation examples:  5000 (for model selection)
Number of test examples:       10000

1) error rate

a) for all 5 runs
    0.1963    0.1397    0.1509    0.1706    0.1421

b) mean
    0.1599

c) standard deviation
    0.0237

2) specificity ( 1 - false positives )

a) for all 5 runs
    0.9356    0.9569    0.8790    0.9319    0.9256

b) mean

    0.9258

c) standard deviation
    0.0287

3) sensitivity (true positives)

a) for all 5 runs
    0.5915    0.6997    0.8010    0.6574    0.7438

b) mean
    0.6987

c) standard deviation
    0.0801