public void init(CY_NeuronLayer CY_NeuronLayer)
{
foreach (CY_Neuron neuron in CY_NeuronLayer.Neurons)
{
neuron.bias = GetRandom(min, max);
}
}
public CY_Neuron(CY_NeuronLayer parent)
{
this.input = 0d;
this.output = 0d;
this.error = 0d;
this.bias = 0d;
this.parent = parent;
}
public void init(CY_NeuronLayer CY_NeuronLayer)
{
int hiddenNeuronCount = 0;
foreach (CY_NeuronToNeuron targetConnector in CY_NeuronLayer.to)
{
hiddenNeuronCount += targetConnector.TargetLayer.neurons.Length;
}
double factor = calcNguyenWidrow(CY_NeuronLayer.neurons.Length, hiddenNeuronCount);
foreach (CY_Neuron neuron in CY_NeuronLayer.Neurons)
{
neuron.bias = GetRandom(-factor, factor);
}
}
protected override void LearnSample(CY_NN_Dataset_Entry e, int currentIteration, int trainingEpochs)
{
int layerCount = layers.Count;
inputLayer.SetInput(e.inputV);
for (int i = 0; i < layerCount; i++)
{
layers[i].calcFire();
}
mse += (outputLayer as CY_NeuronLayer).SetErrors(e.outputV);
for (int i = layerCount; i > 0;)
{
CY_NeuronLayer layer = layers[--i] as CY_NeuronLayer;
if (layer != null)
{
layer.calcError();
}
}
for (int i = 0; i < layerCount; i++)
{
layers[i].Learn(currentIteration, trainingEpochs);
}
}
public CY_NN_Backprop(CY_NeuronLayer inputLayer, CY_NeuronLayer outputLayer)
: base(inputLayer, outputLayer, CY_Train_Method.Supervised)
{
this.mse = 0d;
}