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
    0.2007    0.1386    0.1498    0.1770    0.1459

b) mean
    0.1624

c) standard deviation
    0.0259

2) specificity ( 1 - false positives )

a) for all 5 runs
    0.9322    0.8767    0.8956    0.9189    0.9254

b) mean

    0.9098

c) standard deviation
    0.0231 

3) sensitivity (true positives)

a) for all 5 runs
    0.5856    0.8360    0.7773    0.6619    0.7338

b) mean
    0.7189

c) standard deviation
    0.0979