Round Randomized Learning Vector Quantization for Brain Tumor Imaging
Table 3
MLP, SOM, and RBF configuration.
MLP
RBF
SOM
Random Forest
Decay = true Hidden layers = 5 LR = 0.3 Momentum = 0.2 Training time = 2000 Validation threshold = 20
Seed = 1. The random seed to pass on to -means. maxIts = −1. Maximum number of iterations for the logistic regression to perform. Only applied to discrete class problems. minStdDev = 0.1. Sets the minimum standard deviation for the clusters. numClusters = 2. The number of clusters for -means to generate. Ridge = . Set the ridge value for the logistic or linear regression.
Learning function = linear decay (tangen) Learning rate = 0.3 Map height = 6 Map width = 8 Neighborhood function = Gaussian Neighborhood size = 8 Seed = 1 Supervised = false Number of iterations = 2000
Debug = true Maximum depth = 0 Number of features = 1 Seed = 1