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
    0.0283    0.0295    0.0332    0.0302    0.0312

b) mean
    0.0305

c) standard deviation
    0.0019

2) specificity ( 1 - false positives )

a) for all 5 runs
    0.9805    0.9718    0.9651    0.9722    0.9705

b) mean

    0.9720

c) standard deviation
    0.0055

3) sensitivity (true positives)

a) for all 5 runs
    0.9575    0.9683    0.9695    0.9657    0.9659

b) mean
    0.9654

c) standard deviation
    0.0047