Creating and fitting a deep neural network model for regression

To create and fit a deep neural network model for a regression problem, we will make use of Keras. The code used for the model architecture is as follows:

Note that the input layer having 13 units and the output layer having 1 unit is fixed based on the data; however, to arrive at a suitable number of hidden layers and the number of units in each layer, you need to experiment.

# Model architecture
model <- keras_model_sequential()
model %>%
   layer_dense(units = 10, activation = 'relu', input_shape = c(13)) %>%  
   layer_dense(units = 5, activation = 'relu') %>%
   layer_dense(units = 1) 
summary(model)

OUTPUT
___________________________________________________________________________
Layer (type)                     Output Shape                Param #      
=============================...