Table 2 The parameters of the NN (the multi layer perceptron and the fully-connected multi-hidden layer NN) classifiers and SVM
From: Texture based skin lesion abruptness quantification to detect malignancy
Parameters | NN | Parameters | SVM |
|---|---|---|---|
Learning Rate | 0.001 | Kernel Function | Polynomial |
Number of iteration | 1000 | Polynomial Order | 3 |
Number of run | 20 | Kernel Scale | auto |
Number of hidden layer | 1 | Box constraint | inf |
Number of hidden layer node | 4 | Standardize | TRUE |
Number of hidden layers (If multilayer NN is used) | 4 | Outlier Fraction | 0.05 |