deepNeuralNetwork.build: Build the Neural Network structure and initial values.

In OscarGVelasco/DeepNeuralNetworks4R: Implementation of Deep Neural Networks in R language

Description

'deepNeuralNetwork.build()' returns a DeepMMModel object which contains an initialized deep neural network model with the parameters specified by the user.

Usage

deepNeuralNetwork.build(x, y, HidenLayerNeurons = c(4, 4),
  inputNeurons = 0, outputNeurons = 0, Ai = 0.25, traindata = data,
  drawDNN = FALSE, random.seed = NA, standarization = "r")

Arguments

x	Numeric, complex, or logical vectors.
y	Numeric, complex, or logical vectors.
HidenLayerNeurons	A numeric vector representing the hidden layers. Each number specifies the number of neurons of the corresponding hidden layer.
inputNeurons	Numeric.
outputNeurons	Numeric.
Ai	Numeric.
traindata	Matrix.
drawDNN	Boolean. TRUE draw a representation of the network using ggplot. Default=FALSE.
random.seed	Numeric.
standarization	Character or list. Standarization method to be use. If a list of features (corresponding to rows in the input matrix) is supplied, a standarization feature-z-score is done. "r"=robust median z-score. "s"=standar mean z-score.

Details

This function will create and initialize a deep neural network with a random gaussian distribution the parameters specified by the user will be used to obtain the number of input neurons, number of hidden layers and number of output neurons (which will depend on the number of variables that the model is intended to estimate). The output of this function is intended to be used as the input object of the [deepNeuralNetwork.training] function.

Value

A DeepNNModel object with initialized parameters as specified by the user.

Examples

dnn.model <- deepNeuralNetwork.build(x=c(1,2,4,5),y=3, outputNeurons = 1,
                                     HidenLayerNeurons = c(30,10,3),traindata=data,
                                     random.seed = 1, drawDNN = 0)

## Not run: 
sum("a")

## End(Not run)

OscarGVelasco/DeepNeuralNetworks4R documentation built on Jan. 24, 2021, 12:42 a.m.