public IActivationFunction GetActivationFunction()
{
IActivationFunction activation;
switch (ActivationFunction)
{
case ActivationFunctionType.Linear:
activation = new ActivationLinear();
break;
case ActivationFunctionType.Sigmoid:
activation = new ActivationSigmoid();
break;
case ActivationFunctionType.TanH:
activation = new ActivationTANH();
break;
case ActivationFunctionType.SoftMax:
activation = new ActivationSoftMax();
break;
case ActivationFunctionType.ReLU:
activation = new ActivationReLU();
break;
default:
throw new ArgumentOutOfRangeException();
}
return(activation);
}
private void CBAktywacje_SelectionChanged(object sender, System.Windows.Controls.SelectionChangedEventArgs e)
{
ComboBoxItem typeItem = (ComboBoxItem)CBAktywacje.SelectedItem;
string value = typeItem.Content.ToString();
switch (value)
{
case "Linear":
ActivationFunction = new ActivationLinear();
break;
case "LOG":
ActivationFunction = new ActivationLOG();
break;
case "Sigmoid":
ActivationFunction = new ActivationSigmoid();
break;
case "SIN":
ActivationFunction = new ActivationSIN();
break;
case "TANH":
ActivationFunction = new ActivationTANH();
break;
}
}
public void TestInputIsNormalizedAccordingToTANHFunction()
{
var activationFunction = new ActivationTANH();
double[] input = new[] { -1.3, -0.7, 0.1, 0.3, 1.1, 0.5 };
normalizeStrategy.NormalizeInputInPlace(activationFunction, input);
AssertArraysAreEqual(new[] { -1, -0.7, 0.1, 0.3, 1, 0.5 }, input);
}
public void TestOutputIsNomalizedAccordingToTANHFunction()
{
var activationFunction = new ActivationTANH();
double[] output = new double[] { 1, 0, 1, 0 };
normalizeStrategy.NormalizeOutputInPlace(activationFunction, output);
AssertArraysAreEqual(new double[] { 1, -1, 1, -1 }, output);
}
public void createNetwork()
{
ActivationFunction threshold = new ActivationTANH();
this.network = new FeedforwardNetwork();
this.network.AddLayer(new FeedforwardLayer(threshold, INPUT_SIZE));
this.network.AddLayer(new FeedforwardLayer(threshold,
SineWave.NEURONS_HIDDEN_1));
if (SineWave.NEURONS_HIDDEN_2 > 0)
{
this.network.AddLayer(new FeedforwardLayer(threshold,
SineWave.NEURONS_HIDDEN_2));
}
this.network.AddLayer(new FeedforwardLayer(threshold, OUTPUT_SIZE));
this.network.Reset();
}
public void createNetwork()
{
ActivationFunction threshold = new ActivationTANH();
this.network = new FeedforwardNetwork();
this.network.AddLayer(new FeedforwardLayer(threshold,
PredictSP500.INPUT_SIZE * 2));
this.network.AddLayer(new FeedforwardLayer(threshold,
PredictSP500.NEURONS_HIDDEN_1));
if (PredictSP500.NEURONS_HIDDEN_2 > 0)
{
this.network.AddLayer(new FeedforwardLayer(threshold,
PredictSP500.NEURONS_HIDDEN_2));
}
this.network.AddLayer(new FeedforwardLayer(threshold,
PredictSP500.OUTPUT_SIZE));
this.network.Reset();
}
/// <summary>
/// Creates a feedforward NN
/// </summary>
public virtual void createNetwork()
{
IActivationFunction threshold;
if (ACTIVIATION_FUNCTION == 1)
threshold = new ActivationSigmoid();
else if (ACTIVIATION_FUNCTION == 2)
threshold = new ActivationTANH();
else
throw new System.Exception("Only 2 activation functions have been impletemented.");
network = new BasicNetwork();
network.AddLayer(new BasicLayer(threshold, true, INPUT_NEURONS));
network.AddLayer(new BasicLayer(threshold, true, HIDDENLAYER1_NEURONS));
if (HIDDENLAYER2_NEURONS > 0)
{
network.AddLayer(new BasicLayer(threshold, true, HIDDENLAYER2_NEURONS));
}
network.AddLayer(new BasicLayer(threshold, true, OUTPUT_NEURONS));
network.Structure.FinalizeStructure();
network.Reset();
}
void AddLayers(List <LayerConfig> gen)
{
foreach (var g in gen)
{
IActivationFunction act;
if (g.ActivationType == 0)
{
act = new ActivationBiPolar();
}
switch (g.ActivationType)
{
case 0:
act = new ActivationBiPolar();
break;
case 1:
act = new ActivationBipolarSteepenedSigmoid();
break;
case 2:
act = new ActivationClippedLinear();
break;
case 3:
act = new ActivationCompetitive();
break;
case 4:
act = new ActivationElliott();
break;
case 5:
act = new ActivationElliottSymmetric();
break;
case 6:
act = new ActivationGaussian();
break;
case 7:
act = new ActivationLinear();
break;
case 8:
act = new ActivationLOG();
break;
case 9:
act = new ActivationRamp();
break;
case 10:
act = new ActivationRamp();
break;
case 11:
act = new ActivationSigmoid();
break;
case 12:
act = new ActivationSIN();
break;
case 13:
act = new ActivationSoftMax();
break;
case 14:
act = new ActivationSteepenedSigmoid();
break;
case 15:
act = new ActivationStep();
break;
case 16:
act = new ActivationTANH();
break;
default:
act = new ActivationSoftMax();
break;
}
network.AddLayer(new BasicLayer(act, g.hasBias, g.neurons));
}
}
