/// <summary>
/// Don't use this constructor, it is for serialization only.
/// </summary>
public FreeformPropagationTraining()
: base(TrainingImplementationType.Iterative)
{
_network = null;
_training = null;
FixFlatSopt = true;
}
/// <summary>
/// Construct the trainer.
/// </summary>
/// <param name="theNetwork">The network to train.</param>
/// <param name="theTraining">The training data.</param>
public FreeformPropagationTraining(FreeformNetwork theNetwork,
IMLDataSet theTraining) :
base(TrainingImplementationType.Iterative)
{
_network = theNetwork;
_training = theTraining;
FixFlatSopt = true;
}
/// <summary>
/// Construct a back propagation trainer.
/// </summary>
/// <param name="theNetwork">The network to train.</param>
/// <param name="theTraining">The training data to use. The coefficient for how much of the gradient is applied to each weight.</param>
/// <param name="theLearningRate">The learning rate. The coefficient for how much of the previous delta is applied to each weight.</param>
/// <param name="theMomentum">The momentum.</param>
public FreeformBackPropagation(FreeformNetwork theNetwork,
IMLDataSet theTraining, double theLearningRate,
double theMomentum)
: base(theNetwork, theTraining)
{
theNetwork.TempTrainingAllocate(1, 2);
_learningRate = theLearningRate;
_momentum = theMomentum;
}
/// <summary>
/// Construct a back propagation trainer.
/// </summary>
/// <param name="theNetwork">The network to train.</param>
/// <param name="theTraining">The training data to use. The coefficient for how much of the gradient is applied to each weight.</param>
/// <param name="theLearningRate">The learning rate. The coefficient for how much of the previous delta is applied to each weight.</param>
/// <param name="theMomentum">The momentum.</param>
public FreeformBackPropagation(FreeformNetwork theNetwork,
IMLDataSet theTraining, double theLearningRate,
double theMomentum)
: base(theNetwork, theTraining)
{
theNetwork.TempTrainingAllocate(1, 2);
_learningRate = theLearningRate;
_momentum = theMomentum;
}
/// <summary>
/// Construct the RPROP trainer.
/// </summary>
/// <param name="theNetwork">The network to train.</param>
/// <param name="theTraining">The training set.</param>
/// <param name="initialUpdate">The initial update.</param>
/// <param name="theMaxStep">The max step.</param>
public FreeformResilientPropagation(FreeformNetwork theNetwork,
IMLDataSet theTraining, double initialUpdate,
double theMaxStep)
: base(theNetwork, theTraining)
{
_maxStep = theMaxStep;
theNetwork.TempTrainingAllocate(1, 4);
theNetwork.PerformConnectionTask(c => c.SetTempTraining(TempUpdate,
initialUpdate));
}
public FreeformNetwork Create()
{
FreeformNetwork network = XOR.CreateTrainedFreeformXOR();
XOR.VerifyXOR(network, 0.1);
network.SetProperty("test", "test2");
return(network);
}
public void Execute(IExampleInterface app)
{
TemporalXOR temp = new TemporalXOR();
IMLDataSet trainingSet = temp.Generate(120);
FreeformNetwork elmanNetwork = FreeformNetwork.CreateElman(1, 6, 1, new ActivationSigmoid());
FreeformNetwork feedforwardNetwork = FreeformNetwork.CreateFeedforward(1, 6, 0, 1, new ActivationSigmoid());
double feedforwardError = TrainNetwork("feedforward", feedforwardNetwork, trainingSet);
double elmanError = TrainNetwork("elman", elmanNetwork, trainingSet);
Console.WriteLine(@"Best error rate with Elman Network: " + elmanError);
Console.WriteLine(@"Best error rate with Feedforward Network: "
+ feedforwardError);
Console.WriteLine(@"Elman should be able to get into the 10% range,\nfeedforward should not go below 25%.\nThe recurrent Elment net can learn better in this case.");
Console.WriteLine(@"If your results are not as good, try rerunning, or perhaps training longer.");
EncogFramework.Instance.Shutdown();
}
public static double TrainNetwork(String what,
FreeformNetwork network, IMLDataSet trainingSet)
{
ICalculateScore score = new TrainingSetScore(trainingSet);
IMLTrain trainAlt = new NeuralSimulatedAnnealing(
network, score, 10, 2, 100);
IMLTrain trainMain = new FreeformBackPropagation(network, trainingSet, 0.00001, 0.0);
StopTrainingStrategy stop = new StopTrainingStrategy();
trainMain.AddStrategy(new Greedy());
trainMain.AddStrategy(new HybridStrategy(trainAlt));
trainMain.AddStrategy(stop);
EncogUtility.TrainToError(trainMain, 0.01);
return(trainMain.Error);
}
public void Execute(IExampleInterface app)
{
// create a neural network, without using a factory
var network = new FreeformNetwork();
IFreeformLayer inputLayer = network.CreateInputLayer(2);
IFreeformLayer hiddenLayer1 = network.CreateLayer(3);
IFreeformLayer outputLayer = network.CreateOutputLayer(1);
network.ConnectLayers(inputLayer, hiddenLayer1, new ActivationSigmoid(), 1.0, false);
network.ConnectLayers(hiddenLayer1, outputLayer, new ActivationSigmoid(), 1.0, false);
network.Reset();
// create training data
IMLDataSet trainingSet = new BasicMLDataSet(XORInput, XORIdeal);
EncogUtility.TrainToError(network, trainingSet, 0.01);
EncogUtility.Evaluate(network, trainingSet);
EncogFramework.Instance.Shutdown();
}
public void Execute(IExampleInterface app)
{
// create a neural network, without using a factory
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(null, true, 2));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 3));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), false, 1));
network.Structure.FinalizeStructure();
network.Reset();
// create training data
var trainingSet = new BasicMLDataSet(XORInput, XORIdeal);
EncogUtility.TrainToError(network, trainingSet, 0.01);
EncogUtility.Evaluate(network, trainingSet);
var ff = new FreeformNetwork(network);
EncogUtility.Evaluate(ff, trainingSet);
EncogFramework.Instance.Shutdown();
}
/// <summary>
/// Construct the RPROP trainer.
/// </summary>
/// <param name="theNetwork">The network to train.</param>
/// <param name="theTraining">The training set.</param>
/// <param name="initialUpdate">The initial update.</param>
/// <param name="theMaxStep">The max step.</param>
public FreeformResilientPropagation(FreeformNetwork theNetwork,
IMLDataSet theTraining, double initialUpdate,
double theMaxStep)
: base(theNetwork, theTraining)
{
_maxStep = theMaxStep;
theNetwork.TempTrainingAllocate(1, 4);
theNetwork.PerformConnectionTask(c => c.SetTempTraining(TempUpdate,
initialUpdate));
}
/// <summary>
/// Construct the RPROP trainer, Use default intiial update and max step.
/// </summary>
/// <param name="theNetwork">The network to train.</param>
/// <param name="theTraining">The training set.</param>
public FreeformResilientPropagation(FreeformNetwork theNetwork,
IMLDataSet theTraining)
: this(theNetwork, theTraining, RPROPConst.DefaultInitialUpdate,
RPROPConst.DefaultMaxStep)
{
}
/// <summary>
/// Construct the RPROP trainer, Use default intiial update and max step.
/// </summary>
/// <param name="theNetwork">The network to train.</param>
/// <param name="theTraining">The training set.</param>
public FreeformResilientPropagation(FreeformNetwork theNetwork,
IMLDataSet theTraining)
: this(theNetwork, theTraining, RPROPConst.DefaultInitialUpdate,
RPROPConst.DefaultMaxStep)
{
}
/// <summary>
/// Construct the trainer.
/// </summary>
/// <param name="theNetwork">The network to train.</param>
/// <param name="theTraining">The training data.</param>
public FreeformPropagationTraining(FreeformNetwork theNetwork,
IMLDataSet theTraining)
: base(TrainingImplementationType.Iterative)
{
_network = theNetwork;
_training = theTraining;
FixFlatSopt = true;
}
public void Validate(FreeformNetwork network)
{
network.ClearContext();
XOR.VerifyXOR(network, 0.1);
}
/// <summary>
/// Don't use this constructor, it is for serialization only.
/// </summary>
public FreeformPropagationTraining() : base(TrainingImplementationType.Iterative)
{
_network = null;
_training = null;
FixFlatSopt = true;
}
