View source: R/NeuralNetwork.R
Returns a List which may be used as model.par
of e.g. the function Setup.QLearning()
with the following parameters:
name - Identifier of Model. Per Default \"Neural.Network.Basic\".
setup - Function which should be used to setup the Neural Network. Per Default Setup.Neural.Network
predict - Function which should be used to predict the Neural Network. Per Default Predict.Neural.Network
train - Function which should be used to train/calibrate the Neural Network. Per Default Train.Neural.Network
hidden.nodes - A Vector consisting of the number of Neurons in each hidden layer - e.g. c(25,10) to have two hidden layers with the first layer having 25 Neurons.
activation.hidden - A Vector defining the activation functions of the hidden layers, e.g. c(\"relu\",\"relu\"). Has to have the same number of items as hidden.nodes
. Supported are e.g. relu, tanh, sigmoid and linear
activation.output Activiation function of the output layer. Supported are e.g. relu, tanh, sigmoid and linear.
dropout - A Vector consisting of the dropout rate of the hidden layers - e.g. c(0.2,0.2) if one wants both hidden layers to have a dropout of 20 Percent.
input.dropout - Dropout of the input layer.
loss Specifies the loss function, e.g. \'mse\'
optimizer. Specifies the used optimizer. By Default Adam Optimization is used with a Learning rate of 0.001.
epochs How many epochs should the Neural Network be trained?
batch.size Batch Size of Neural Network.
verbose Should the Neural Network give an output? 0 for no output, 1 for output for each epoch, 2 for aggregate output every other epoch.
1 | Get.Def.Par.Neural.Network(setting = NULL)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.