Skip to main content

Advertisement

Table 2 Explored classifier architectures

From: An artificial neural networks approach for assessment treatment response in oncological patients using PET/CT images

Classifier Parameters Values
MLPI number of hidden layers 1
  number of neurons in the hidden layer: even numbers in [6,28]
MLPII number of hidden layers 2
  number of neurons:  
  – first hidden layer even numbers in [6,28]
  – second hidden layer half the number of neurons of the first layer
LVQNN number of neurons in the hidden layer even numbers in [6,28]
RBFNN spread value powers of two with integer exponents in [-1,15]
PNN spread value powers of two with integer exponents in [-1,15]
k-NN number of neighbors integers in [1,15]