LDNN (version 1.10)

create_model: Pre-defined Neural Network for Longitudinal Data

Description

Create the Neural Network model (Keras).

Usage

create_model(
  rnn_inputs,
  recurrent_droppout,
  inputs,
  layer_dropout,
  n_nodes_hidden_layers,
  loss_function,
  opt,
  metric
)

Arguments

rnn_inputs

The number of inputs (integers) per each LSTM (vector of length 10).

recurrent_droppout

The dropout to be applied in the LSTMs (between 0 and 1).

inputs

The number of inputs (integer) to be concatenated with the output of the LSTMs.

layer_dropout

The dropout to be applied between the hidden layers (between 0 and 1).

n_nodes_hidden_layers

The number of nodes in the hidden layers (2 in total).

loss_function

The loss function to be used.

opt

The optimizer to be used.

metric

The metric to be used.

Value

The model object built in Keras.

Examples

# NOT RUN {
inp = c(20,24,24,24,16,16,16,16,16,15)
rec_drop = rep(0.1,10)
l_drop = c(0.1,0.1)
# }
# NOT RUN {
create_model(inp,rec_drop,232,c(0.1,0.1),l_drop,'mean_squared_error','adam','mean_absolute_error')
# }
# NOT RUN {
# The functions require to have python installed
# As well as tensorflow, keras and reticulate package.
# }