Threshold activation function.
The class represents threshold activation function with the next expression: f(x) = 1, if x >= 0, otherwise 0
Output range of the function: [0, 1].
Functions graph:
void Proc2(Model model)
{
int learnIterations = 100;
double desiredError = 0;
var activationFunc1 = new ThresholdFunction();
var activationFunc2 = new SigmoidFunction(1);
IActivationFunction activationFunc = activationFunc2;
int inputsCount = model.InputsCount;
int[] neuronsCount = new int[3];
neuronsCount[0] = model.InputsCount;
neuronsCount[1] = model.InputsCount * 2;
neuronsCount[2] = model.desiredOutput[0].Length;
ActivationNetwork net = new ActivationNetwork(activationFunc, inputsCount, neuronsCount);
BackPropagationLearning lerning = new BackPropagationLearning(net);
ErrorCalculator errorCalculator = new ErrorCalculator();
Process(learnIterations, desiredError, net, lerning,
model.input, model.desiredOutput, errorCalculator);
Console.ReadLine();
}
public NetworkContainer CreateNetworkContainer()
{
NetworkContainer neuralNetwork = null;
int[] hiddenLayers = new int[cbHiddenLayerNumber.SelectedIndex];
switch (hiddenLayers.Length)
{
case 0:
break;
case 1:
hiddenLayers[0] = (int)this.nHidden1.Value;
break;
case 2:
hiddenLayers[1] = (int)this.nHidden2.Value;
goto case 1;
case 3:
hiddenLayers[2] = (int)this.nHidden3.Value;
goto case 2;
case 4:
hiddenLayers[3] = (int)this.nHidden4.Value;
goto case 3;
default:
break;
}
IActivationFunction activationFunction = null;
if (this.rbBipolarSigmoid.Checked)
{
activationFunction = new BipolarSigmoidFunction((double)numSigmoidAlpha.Value);
}
else if (this.rbSigmoid.Checked)
{
activationFunction = new SigmoidFunction((double)numSigmoidAlpha.Value);
}
else if (this.rbThreshold.Checked)
{
activationFunction = new ThresholdFunction();
}
neuralNetwork = new NetworkContainer(
tbNetworkName.Text,
m_networkSchema,
activationFunction,
hiddenLayers);
// neuralNetwork.Schema.DataRanges.ActivationFunctionRange = new AForge.DoubleRange((double)numRangeLow.Value, (double)numRangeHigh.Value);
return neuralNetwork;
}
void Proc1()
{
int learnIterations = 100;
double desiredError = 0;
Model model = getModelAnd();
var activationFunc1 = new ThresholdFunction();
var activationFunc2 = new SigmoidFunction(1);
IActivationFunction activationFunc = activationFunc2;
int inputsCount = model.InputsCount;
int neuronsCount = 1;
ActivationNetwork net = new ActivationNetwork(activationFunc, inputsCount, neuronsCount);
PerceptronLearning lerning = new PerceptronLearning(net);
ErrorCalculator errorCalculator = new ErrorCalculator();
Process(learnIterations, desiredError, net, lerning,
model.input, model.desiredOutput, errorCalculator);
Console.ReadLine();
}