Table 3 The first 10 smallest mean values of the error δ for 59 test patients for different configurations of features, j = 1000 randomisations and 1000 iterations for each randomisation and the number of neurons in the hidden layer s = 150
From: Corneal power evaluation after myopic corneal refractive surgery using artificial neural networks
Feature (“0” absent, “1” present) | δ [D] | δ max [D] | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
w(1) | w(2) | w(3) | w(4) | w(5) | w(6) | w(7) | w(8) | w(9) | w(10) | ||
0 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 1 | 0.16 | 0.75 |
0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 1 | 0.19 | 0.72 |
0 | 1 | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 0 | 0.19 | 0.8 |
0 | 0 | 0 | 1 | 0 | 1 | 0 | 1 | 0 | 1 | 0.29 | 0.8 |
0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 1 | 0.36 | 0.9 |
0 | 1 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 1 | 0.36 | 1.1 |
0 | 0 | 0 | 1 | 1 | 0 | 0 | 1 | 1 | 1 | 0.37 | 0.8 |
0 | 0 | 0 | 1 | 1 | 0 | 1 | 1 | 1 | 1 | 0.39 | 0.8 |
0 | 0 | 0 | 0 | 1 | 0 | 1 | 1 | 1 | 1 | 0.40 | 1.1 |
0 | 1 | 0 | 1 | 1 | 0 | 1 | 1 | 0 | 1 | 0.40 | 1.2 |