create_network: Create a neural network base structure

In eduardokapp/r_neural_network: Kapp Neural Nets

Description

This function generates a network object represented as a list. The list contains all the information about the network, such as input size, output size, number of hidden layers, hidden layers sizes.

Usage

create_network(
  input_size,
  n_layers = 1,
  layer_sizes = c(1),
  activations = c("sigmoid")
)

Arguments

input_size	The network input size (integer)
n_layers	Number of hidden layers to be used. Note that this includes the output layer. (integer)
layer_sizes	An array with the number of neurons for each layer. For example, if there are two layers, each with 30 neurons, then layer_sizes must be c(30, 30). (integer array)
activations	An array indicating what activation functions should be used for each layer. By default, sigmoid functions are used. (character)

Value

A network layer object represented as a list.

Author(s)

Eduardo Kapp

eduardokapp/r_neural_network documentation built on Dec. 20, 2021, 3:21 a.m.