dNNmodel {dnn}

Specify a deep neural network model

Description

{dNNmodel} is an R function to create a deep neural network model that is to be used in the feed forward network { fwdNN } and back propagation { bwdNN }.

Usage

  dNNmodel(units, activation=NULL, input_shape = NULL, type = NULL, 
           N = NULL, Rcpp=TRUE, optimizer = c("momentum", "nag", "adam"))

Arguments

units

number of nodes for each layer

activation

activation function

input_shape

the number of columns of input X, default is NULL.

N

the number of training sample, default is NULL.

type

default is "dense", currently only support dense layer.

Rcpp

use Rcpp (C++ for R) to speed up the fwdNN and bwdNN, default is "TRUE".

optimizer

optimizer used in SGD, default is "momentum".

Details

dNNmodel returns an object of class "dNNmodel".

The function "print" (i.e., "print.dNNmodel") can be used to print a summary of the dnn model,

The function "summary" (i.e., "summary.dNNmodel") can be used to print a summary of the dnn model,

Value

An object of class "dNNmodel" is a list containing at least the following components:

units

number of nodes for each layer

activation

activation function

drvfun

derivative of the activation function

params

the initial values of the parameters, to be updated in model training.

input_shape

the number of columns of input X, default is NULL.

N

the number of training sample, default is NULL.

type

default is "dense", currently only support dense layer.

Author(s)

Bingshu E. Chen ([e-mail])

See Also

plot.dNNmodel, print.dNNmodel, summary.dNNmodel, fwdNN, bwdNN, optimizerSGD, optimizerNAG,

Examples

### To define a dnn model
 model = dNNmodel(units = c(8, 6, 1), activation = c("relu", "sigmoid", "sigmoid"), 
         input_shape = c(3))