/// <summary>
/// Create a feedforward freeform neural network.
/// </summary>
/// <param name="input">The input count.</param>
/// <param name="hidden1">The first hidden layer count, zero if none.</param>
/// <param name="hidden2">The second hidden layer count, zero if none.</param>
/// <param name="output">The output count.</param>
/// <param name="af">The activation function.</param>
/// <returns>The newly crated network.</returns>
public static FreeformNetwork CreateFeedforward(int input,
int hidden1, int hidden2, int output,
IActivationFunction af)
{
var network = new FreeformNetwork();
IFreeformLayer lastLayer = network.CreateInputLayer(input);
IFreeformLayer currentLayer;
if (hidden1 > 0)
{
currentLayer = network.CreateLayer(hidden1);
network.ConnectLayers(lastLayer, currentLayer, af, 1.0, false);
lastLayer = currentLayer;
}
if (hidden2 > 0)
{
currentLayer = network.CreateLayer(hidden2);
network.ConnectLayers(lastLayer, currentLayer, af, 1.0, false);
lastLayer = currentLayer;
}
currentLayer = network.CreateOutputLayer(output);
network.ConnectLayers(lastLayer, currentLayer, af, 1.0, false);
network.Reset();
return(network);
}
/// <summary>
/// Construct an Elmann recurrent neural network.
/// </summary>
/// <param name="input">The input count.</param>
/// <param name="hidden1">The hidden count.</param>
/// <param name="output">The output count.</param>
/// <param name="af">The activation function.</param>
/// <returns>The newly created network.</returns>
public static FreeformNetwork CreateElman(int input,
int hidden1, int output, IActivationFunction af)
{
var network = new FreeformNetwork();
IFreeformLayer inputLayer = network.CreateInputLayer(input);
IFreeformLayer hiddenLayer1 = network.CreateLayer(hidden1);
IFreeformLayer outputLayer = network.CreateOutputLayer(output);
network.ConnectLayers(inputLayer, hiddenLayer1, af, 1.0, false);
network.ConnectLayers(hiddenLayer1, outputLayer, af, 1.0, false);
network.CreateContext(hiddenLayer1, hiddenLayer1);
network.Reset();
return(network);
}
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 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();
}
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 Validate(FreeformNetwork network)
{
network.ClearContext();
XOR.VerifyXOR(network, 0.1);
}
/// <summary>
/// Create a feedforward freeform neural network.
/// </summary>
/// <param name="input">The input count.</param>
/// <param name="hidden1">The first hidden layer count, zero if none.</param>
/// <param name="hidden2">The second hidden layer count, zero if none.</param>
/// <param name="output">The output count.</param>
/// <param name="af">The activation function.</param>
/// <returns>The newly crated network.</returns>
public static FreeformNetwork CreateFeedforward(int input,
int hidden1, int hidden2, int output,
IActivationFunction af)
{
var network = new FreeformNetwork();
IFreeformLayer lastLayer = network.CreateInputLayer(input);
IFreeformLayer currentLayer;
if (hidden1 > 0)
{
currentLayer = network.CreateLayer(hidden1);
network.ConnectLayers(lastLayer, currentLayer, af, 1.0, false);
lastLayer = currentLayer;
}
if (hidden2 > 0)
{
currentLayer = network.CreateLayer(hidden2);
network.ConnectLayers(lastLayer, currentLayer, af, 1.0, false);
lastLayer = currentLayer;
}
currentLayer = network.CreateOutputLayer(output);
network.ConnectLayers(lastLayer, currentLayer, af, 1.0, false);
network.Reset();
return network;
}
/// <summary>
/// Construct an Elmann recurrent neural network.
/// </summary>
/// <param name="input">The input count.</param>
/// <param name="hidden1">The hidden count.</param>
/// <param name="output">The output count.</param>
/// <param name="af">The activation function.</param>
/// <returns>The newly created network.</returns>
public static FreeformNetwork CreateElman(int input,
int hidden1, int output, IActivationFunction af)
{
var network = new FreeformNetwork();
IFreeformLayer inputLayer = network.CreateInputLayer(input);
IFreeformLayer hiddenLayer1 = network.CreateLayer(hidden1);
IFreeformLayer outputLayer = network.CreateOutputLayer(output);
network.ConnectLayers(inputLayer, hiddenLayer1, af, 1.0, false);
network.ConnectLayers(hiddenLayer1, outputLayer, af, 1.0, false);
network.CreateContext(hiddenLayer1, hiddenLayer1);
network.Reset();
return network;
}
