build_keras_net: Build a Keras Multilayer Perceptron

In RaphaelS1/survivalmodels: Models for Survival Analysis

Build a Keras Multilayer Perceptron

Description

Utility function to build a Keras MLP.

Usage

build_keras_net(
  n_in,
  n_out,
  nodes = c(32L, 32L),
  layer_pars = list(),
  activation = "linear",
  act_pars = list(),
  dropout = 0.1,
  batch_norm = TRUE,
  batch_pars = list()
)

Arguments

n_in	(integer(1)) Number of input features.
n_out	(integer(1)) Number of targets.
nodes	(numeric()) Hidden nodes in network, each element in vector represents number of hidden nodes in respective layer.
layer_pars	(list()) Arguments passed to keras::layer_dense.
activation	(character(1)) Activation function passed to keras::layer_activation. Default is linear.
act_pars	(list()) Parameters for activation function, see keras::layer_activation.
dropout	(numeric(1)) Optional dropout layer, if NULL then no dropout layer added otherwise either same dropout will be added to all layers.
batch_norm	(logical(1)) If TRUE (default) then batch normalisation is applied to all layers.
batch_pars	(list()) Parameters for batch normalisation, see keras::layer_batch_normalization.

Details

This function is a helper for R users with less Python experience. Currently it is limited to simple MLPs and with identical layers. More advanced networks will require manual creation with keras.

Examples

if (requireNamespaces("keras")) {
  build_keras_net(4L, 2L)

  build_keras_net(n_in = 4L, n_out = 2L, nodes = c(32L, 64L, 32L),
    activation = "elu", dropout = 0.4)
}

RaphaelS1/survivalmodels documentation built on July 5, 2024, 10:17 a.m.