private static void Train()
{
Console.WriteLine("Network Training");
PrintUnderline(50);
Console.WriteLine("\t1. Train to minimum error");
Console.WriteLine("\t2. Train to max epoch");
Console.WriteLine("\t3. Network Menu");
PrintNewLine();
//BackPropTrainParams trainParams = null;
BackPropLearning learning = null;
switch (GetInput("\tYour Choice: ", 1, 3))
{
case 1:
var minError = GetDouble("\tMinimum Error: ", 0.000000001, 1.0);
PrintNewLine();
Console.WriteLine("\tTraining...");
//trainParams = new BackPropTrainParams { Training = TrainingType.MinimumError, MinimumError = minError };
learning = new BackPropLearning(_network)
{
MinimumError = minError
};
learning.TrainByError(_dataSets);
//_network.Train(_dataSets, trainParams);
Console.WriteLine("\t**Training Complete**");
PrintNewLine();
NetworkMenu();
break;
case 2:
var maxEpoch = GetInput("\tMax Epoch: ", 1, int.MaxValue);
if (!maxEpoch.HasValue)
{
PrintNewLine();
NetworkMenu();
return;
}
PrintNewLine();
Console.WriteLine("\tTraining...");
learning = new BackPropLearning(_network)
{
NumEpochs = maxEpoch.Value
};
learning.TrainByEpochs(_dataSets);
Console.WriteLine("\t**Training Complete**");
PrintNewLine();
break;
case 3:
NetworkMenu();
break;
}
PrintNewLine();
}
public void BackPropRationalSigmoidXorTest()
{
var nnet = new Network(2, new int[] { 2 }, 1, typeof(RationalSigmoid), typeof(RationalSigmoid));
var learning = new BackPropLearning(nnet)
{
MinimumError = 0.1,
Momentum = 0.5,
LearnRate = 0.1
};
learning.TrainByError(BuildXorDataSets(), 20000);
System.Diagnostics.Debug.WriteLine("trained in {0} epochs", learning.ResultEpochs);
CheckResults(nnet, 0.15);
}
