/// <summary>
/// Calculate the current error.
/// </summary>
public void CalcError()
{
BackpropagationLayer next = this.backpropagation
.GetBackpropagationLayer(this.layer.Next);
for (int i = 0; i < this.layer.Next.NeuronCount; i++)
{
for (int j = 0; j < this.layer.NeuronCount; j++)
{
AccumulateMatrixDelta(j, i, next.GetErrorDelta(i)
* this.layer.GetFire(j));
SetError(j, GetError(j) + this.layer.LayerMatrix[j, i]
* next.GetErrorDelta(i));
}
AccumulateThresholdDelta(i, next.GetErrorDelta(i));
}
if (this.layer.IsHidden())
{
// hidden layer deltas
for (int i = 0; i < this.layer.NeuronCount; i++)
{
SetErrorDelta(i, BoundNumbers.Bound(CalculateDelta(i)));
}
}
}
/// <summary>
/// Get the BackpropagationLayer that corresponds to the specified layer.
/// </summary>
/// <param name="layer">The specified layer.</param>
/// <returns>The BackpropagationLayer that corresponds to the specified layer.</returns>
public BackpropagationLayer GetBackpropagationLayer(
FeedforwardLayer layer)
{
BackpropagationLayer result = this.layerMap[layer];
if (result == null)
{
throw new NeuralNetworkError(
"Layer unknown to backpropagation trainer, was a layer added after training begain?");
}
return(result);
}
/// <summary>
/// The rate at which the weight matrix will be adjusted based on
/// learning.
/// </summary>
/// <param name="network">The neural network to be trained.</param>
/// <param name="input">The input values to the neural network.</param>
/// <param name="ideal">The ideal values expected from the neural network.</param>
/// <param name="learnRate">The learning rate, how fast to modify neural network values.</param>
/// <param name="momentum">The momentum, how much to use the previous training iteration for the current.</param>
public Backpropagation(FeedforwardNetwork network,
double[][] input, double[][] ideal,
double learnRate, double momentum)
{
this.network = network;
this.learnRate = learnRate;
this.momentum = momentum;
this.input = input;
this.ideal = ideal;
foreach (FeedforwardLayer layer in network.Layers)
{
BackpropagationLayer bpl = new BackpropagationLayer(this,
layer);
this.layerMap.Add(layer, bpl);
}
}
/// <summary>
/// The rate at which the weight matrix will be adjusted based on
/// learning.
/// </summary>
/// <param name="network">The neural network to be trained.</param>
/// <param name="input">The input values to the neural network.</param>
/// <param name="ideal">The ideal values expected from the neural network.</param>
/// <param name="learnRate">The learning rate, how fast to modify neural network values.</param>
/// <param name="momentum">The momentum, how much to use the previous training iteration for the current.</param>
public Backpropagation(FeedforwardNetwork network,
double[][] input, double[][] ideal,
double learnRate, double momentum)
{
this.network = network;
this.learnRate = learnRate;
this.momentum = momentum;
this.input = input;
this.ideal = ideal;
foreach (FeedforwardLayer layer in network.Layers)
{
BackpropagationLayer bpl = new BackpropagationLayer(this,
layer);
this.layerMap.Add(layer, bpl);
}
}