Module
Module is an abstract class which defines fundamental methods necessary for a training a neural network. Modules are serializable.
Modules contain two states variables: output and gradInput.
output
gradInput
[output] forward(input)
[gradInput] backward(input, gradOutput)
zeroGradParameters()
updateParameters(learningRate)
share(mlp,s1,s2,...,sn)
clone(mlp,...)