MLP module for GPD parameter prediction

A fully-connected network (or multi-layer perception) as a torch::nn_module, designed for generalized Pareto distribution parameter prediction.

Usage

FC_GPD_net(
  D_in,
  Hidden_vect = c(5, 5, 5),
  activation = torch::nnf_sigmoid,
  p_drop = 0,
  shape_fixed = FALSE,
  device = default_device()
)

D_in: the input size (i.e. the number of features),
Hidden_vect: a vector of integers whose length determines the number of layers in the neural network and entries the number of neurons in each corresponding successive layer,
activation: the activation function for the hidden layers (should be either a callable function, preferably from the torch library),
p_drop: probability parameter for dropout before each hidden layer for regularization during training,
shape_fixed: whether the shape estimate depends on the covariates or not (bool),
device: a torch::torch_device() for an internal constant vector. Defaults to default_device().

The constructor allows specifying:

D_inthe input size (i.e. the number of features),
Hidden_vecta vector of integers whose length determines the number of layers in the neural network and entries the number of neurons in each corresponding successive layer,
activationthe activation function for the hidden layers (should be either a callable function, preferably from the torch library),
p_dropprobability parameter for dropout before each hidden layer for regularization during training,
shape_fixedwhether the shape estimate depends on the covariates or not (bool),
devicea torch::torch_device() for an internal constant vector. Defaults to default_device().