/// <inheritdoc />
public override BasicNetwork Calculate()
{
//Network
var network = new BasicNetwork();
var inputNeuronCount = inputs.GetLength(1);
var outputNeuronCount = targets.GetLength(1);
//Input Layer
var inputLayer = new BasicLayer(inputActivationFunction, inputHasBias, inputNeuronCount);
network.AddLayer(inputLayer);
//Hidden Layer
if (hiddenLayerConfig.GetLength(1) != 2)
{
throw new ArgumentException("Net Configuration is a 2 column table of values of neuron count and activation function type, with each row representing a separate layer");
}
for (var row = 0; row < hiddenLayerConfig.GetLength(0); row++)
{
var activationFunc = Util.GetActivationFunction(hiddenLayerConfig[row, 1].ToString());
var layer = new BasicLayer(activationFunc, true, Convert.ToInt32(hiddenLayerConfig[row, 0]));
network.AddLayer(layer);
}
//Output layer
var outputLayer = new BasicLayer(outputActivationFunction, outputHasBias, outputNeuronCount);
network.AddLayer(outputLayer);
//Training
network.Structure.FinalizeStructure();
network.Reset();
var dataSet = new BasicMLDataSet(inputs.AsJagged(), targets.AsJagged());
var trainlm = new LevenbergMarquardtTraining(network, dataSet);
var epoch = 1;
do
{
trainlm.Iteration();
epoch++;
} while (epoch < epochLimit && trainlm.Error > errorTolerance);
return(network);
}
