Table 2 Examples of hyperparameters of machine learning methods
Method | Hyperparameters |
|---|---|
Neural network | Learning rate Momentum Weight decay Epochs Batch size Number of hidden layers Neurons per hidden layer Neuron's activation function Regularisation Dropout Weight and bias initiation loss function Output function number of classes [47] |
Convolutional neural network (spatial feature learning) | Patch size Convolutional layers Fully connected layers Number of filters Filter size [48] |
Support vector machine | Kernel Cost Gamma Degree [49] |
k-nearest neighbour | K |
Linear discriminant analysis | None |
Clustering | N clusters Distance function |