/* dodano dla samouczacego sie neuronu */
public void Learn(TeachingSet.Element teachingElement, int neuronIndex, double etha)
{
_neurons[neuronIndex].LearnSelf(
teachingElement.Inputs,
etha
);
}
public void LearnSimple(TeachingSet.Element teachingElement, double ratio,
ref double[] previousResponse, ref double[] previousError,
LearningMethod method)
{
if (_layers.Count != 1)
{
throw new InvalidOperationException(
"The simple learning algorithm can be applied only to one-layer networks.");
}
NonLinearNeuron[] layer = _layers[0];
if (previousResponse == null)
{
previousResponse = new double[layer.Length];
}
if (previousError == null)
{
previousError = new double[layer.Length];
}
double[] actualInputs = AppendBias(teachingElement.Inputs, false);
for (int neuronIndex = 0; neuronIndex < layer.Length; neuronIndex++)
{
switch (method)
{
case LearningMethod.Perceptron:
layer[neuronIndex].Learn(
actualInputs,
teachingElement.ExpectedOutputs[neuronIndex],
ratio,
out previousResponse[neuronIndex],
out previousError[neuronIndex]
);
break;
case LearningMethod.WidrowHoff:
layer[neuronIndex].LearnWidrowHoff(
actualInputs,
teachingElement.ExpectedOutputs[neuronIndex],
ratio,
out previousResponse[neuronIndex],
out previousError[neuronIndex]
);
break;
}
}
}
public void Learn(TeachingSet.Element teachingElement, double etha)
{
double _max = 0;
_max = Winner(teachingElement.Inputs);
for (int x = 1; x < _neurons.Length; x++)
{
}
for (int neuronIndex = 0; neuronIndex < _neurons.Length; neuronIndex++)
{
_neurons[neuronIndex].Learn(
teachingElement.Inputs,
etha,
_max
);
}
}
public void Learn(TeachingSet.Element teachingElement, double ratio,
ref double[] previousResponse, ref double[] previousError)
{
if (previousResponse == null)
{
previousResponse = new double[_neurons.Length];
}
if (previousError == null)
{
previousError = new double[_neurons.Length];
}
for (int neuronIndex = 0; neuronIndex < _neurons.Length; neuronIndex++)
{
_neurons[neuronIndex].Learn(
teachingElement.Inputs,
teachingElement.ExpectedOutputs[neuronIndex],
ratio,
out previousResponse[neuronIndex],
out previousError[neuronIndex]
);
}
}
public void LearnSimpleWidrowHoff(TeachingSet.Element teachingElement,
double ratio, ref double[] previousResponse, ref double[] previousError)
{
LearnSimple(teachingElement, ratio, ref previousResponse,
ref previousError, LearningMethod.WidrowHoff);
}
public void LearnSimple(TeachingSet.Element teachingElement, double ratio,
ref double[] previousResponse, ref double[] previousError)
{
LearnSimple(teachingElement, ratio, ref previousResponse,
ref previousError, LearningMethod.Perceptron);
}
