Create a new CNN model

cnn {CNN}

R Documentation

Create a new CNN model

Description

Convolutional neural network (CNN) is a regularized type of feed-forward
neural network that learns feature engineering by itself via filters
(or kernel) optimization. Vanishing gradients and exploding gradients,
seen during backpropagation in earlier neural networks, are prevented by
using regularized weights over fewer connections.

Usage

cnn(
    file = NULL);

Arguments

file

if the given model file parameter is not default nothing, then the new CNN model object will be loaded from the specific given file, otherwise a blank new model object will be created from the CNN layer model builder.

env

[as Environment]

Authors

MLkit

Value

this function returns data object in these one of the listed data types: ConvolutionalNN, LayerBuilder.

clr value class

ConvolutionalNN
LayerBuilder

[Package CNN version 1.0.0.0 Index]